com.framesail/framesail is an MCP server published by com.framesail, hosted at api.framesail.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 28 tools, including get_status, view_image, get_generation_options, account_edit, delete.
Create long-form YouTube videos end to end: script, storyboard, voiceover, final MP4.
Nothing else in the archive shares these values.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Where things stand and what to do next; start and resume here. Always reports the account: plan, credits, credits held by running jobs, and credits_available to spend. project_id adds the project's settings, each step's state and web link, jobs with readable errors, export_url, next_step and, when something failed, failures: the last failed jobs and the failed segments grouped by kind and error. channel_id reports the channel style instead: analysis_done, inputs_stale, templates, templates_stale and next_step. Without API access it reports only the account and subscription_needed: pass that on to the user.
| Parameter | Type | Description |
|---|---|---|
| wait | boolean | Wait up to about 50 seconds for the jobs in scope to finish, then report only credits, jobs, step states and next_step; call again if some still run |
| channel_id | any | Report this channel's style instead of a project |
| project_id | any | Project id |
None yet. Changes appear after a server's second daily check.
{
"name": "get_status",
"title": "Get status",
"description": "Where things stand and what to do next; start and resume here.\n\nAlways reports the account: plan, credits, credits held by running jobs,\nand credits_available to spend. project_id adds the project's settings,\neach step's state and web link, jobs with readable errors, export_url,\nnext_step and, when something failed, failures: the last failed jobs and\nthe failed segments grouped by kind and error. channel_id reports the channel style instead:\nanalysis_done, inputs_stale, templates, templates_stale and next_step.\nWithout API access it reports only the account and\nsubscription_needed: pass that on to the user.",
"inputSchema": {
"type": "object",
"properties": {
"wait": {
"type": "boolean",
"default": false,
"description": "Wait up to about 50 seconds for the jobs in scope to finish, then report only credits, jobs, step states and next_step; call again if some still run"
},
"channel_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Report this channel's style instead of a project"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
}
}
},
"annotations": {
"title": "Get status",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Show a Framesail image inline: a segment image, reference image, style template or preset preview.
| Parameter | Type | Description |
|---|---|---|
| url * | string | An image URL from a read tool (public_url, reference_image, template or preset); other hosts are refused |
{
"name": "view_image",
"title": "View image",
"description": "Show a Framesail image inline: a segment image, reference image,\nstyle template or preset preview.",
"inputSchema": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"description": "An image URL from a read tool (public_url, reference_image, template or preset); other hosts are refused"
}
}
},
"annotations": {
"title": "View image",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}What a generate call can be told to use. models: the allowed models with credit estimates and settings_schema (the valid settings keys); is_default marks the default (the account's saved choice, else Framesail's). Voice and clip models come in families, each with its own default: pass provider or talking_head for one family. prompt_sections: sections with entity_backed=false can be overridden with editable_sections; entity_backed=true sections show the item's own content (description, prompts, text, brief): change it with the edit tools.
| Parameter | Type | Description |
|---|---|---|
| action * | string | models: the allowed models; prompt_sections: the prompt editor's sections |
| provider | any | voice_block: the voice engine (the project's voice_tts_provider) |
| generation * | string | script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images |
| talking_head | any | segment_video: true for talking head models, false for clips |
{
"name": "get_generation_options",
"title": "Get generation options",
"description": "What a generate call can be told to use.\n\nmodels: the allowed models with credit estimates and settings_schema\n(the valid settings keys); is_default marks the default (the account's\nsaved choice, else Framesail's). Voice and clip models come in families,\neach with its own default: pass provider or talking_head for one family.\n\nprompt_sections: sections with entity_backed=false can be overridden\nwith editable_sections; entity_backed=true sections show the item's own\ncontent (description, prompts, text, brief): change it with the edit\ntools.",
"inputSchema": {
"type": "object",
"required": [
"generation",
"action"
],
"properties": {
"action": {
"enum": [
"models",
"prompt_sections"
],
"type": "string",
"description": "models: the allowed models; prompt_sections: the prompt editor's sections"
},
"provider": {
"anyOf": [
{
"enum": [
"minimax",
"elevenlabs"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "voice_block: the voice engine (the project's voice_tts_provider)"
},
"generation": {
"enum": [
"script",
"script_scan",
"storyboard",
"character_reference",
"environment_reference",
"object_reference",
"voice_block",
"segment_image",
"segment_video",
"art_style_character_template",
"art_style_environment_template"
],
"type": "string",
"description": "script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images"
},
"talking_head": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "segment_video: true for talking head models, false for clips"
}
}
},
"annotations": {
"title": "Get generation options",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}The account's default model and settings for one kind of generation, used when neither the call nor the item's prompt editor names one. voice_block needs provider and segment_video needs talking_head: each family keeps its own default.
| Parameter | Type | Description |
|---|---|---|
| model | any | set_model_default: a model id from get_generation_options |
| action * | string | set_model_default: model, optional settings; clear_model_default |
| provider | any | voice_block: the voice engine (the project's voice_tts_provider) |
| settings | any | Model settings: keys of its settings_schema |
| generation * | string | script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images |
| talking_head | any | segment_video: true for talking head models, false for clips |
{
"name": "account_edit",
"title": "Edit account",
"description": "The account's default model and settings for one kind of generation,\nused when neither the call nor the item's prompt editor names one.\nvoice_block needs provider and segment_video needs talking_head: each\nfamily keeps its own default.",
"inputSchema": {
"type": "object",
"required": [
"action",
"generation"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_model_default: a model id from get_generation_options"
},
"action": {
"enum": [
"set_model_default",
"clear_model_default"
],
"type": "string",
"description": "set_model_default: model, optional settings; clear_model_default"
},
"provider": {
"anyOf": [
{
"enum": [
"minimax",
"elevenlabs"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "voice_block: the voice engine (the project's voice_tts_provider)"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"generation": {
"enum": [
"script",
"script_scan",
"storyboard",
"character_reference",
"environment_reference",
"object_reference",
"voice_block",
"segment_image",
"segment_video",
"art_style_character_template",
"art_style_environment_template"
],
"type": "string",
"description": "script_scan is Analyze Script; *_reference, reference images; voice_block, the voiceover; segment_image, a segment's image; segment_video, a clip; art_style_*_template, the style's template images"
},
"talking_head": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "segment_video: true for talking head models, false for clips"
}
}
},
"annotations": {
"title": "Edit account",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Delete; confirm with the user first. A project or music track is deleted for good; an asset or segment_extra is removed to the bin. project: it and everything in it. asset: a character, environment or object. music_track: a background music track. segment_extra: a segment's sound effect or overlay, with its scene layers. A segment's image, clip and voiceover can't be deleted.
| Parameter | Type | Description |
|---|---|---|
| id | any | The asset, music track, or segment sound effect or overlay |
| type * | string | project: project_id; asset, music_track: id; segment_extra: project_id, segment_number, and id if the segment has several |
| project_id | any | Project id |
| segment_number | any | Segment number (1-based, from storyboard_read) |
{
"name": "delete",
"title": "Delete",
"description": "Delete; confirm with the user first. A project or music track is\ndeleted for good; an asset or segment_extra is removed to the bin.\nproject: it and everything in it. asset: a character, environment or\nobject. music_track: a background music track. segment_extra: a\nsegment's sound effect or overlay, with its scene layers. A segment's\nimage, clip and voiceover can't be deleted.",
"inputSchema": {
"type": "object",
"required": [
"type"
],
"properties": {
"id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The asset, music track, or segment sound effect or overlay"
},
"type": {
"enum": [
"project",
"asset",
"music_track",
"segment_extra"
],
"type": "string",
"description": "project: project_id; asset, music_track: id; segment_extra: project_id, segment_number, and id if the segment has several"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"segment_number": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Segment number (1-based, from storyboard_read)"
}
}
},
"annotations": {
"title": "Delete",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Your channels, or the projects in one channel.
| Parameter | Type | Description |
|---|---|---|
| action * | string | channels: your channels; projects: the projects in channel_id |
| channel_id | any | projects: the channel |
{
"name": "projects_read",
"title": "Read channels and projects",
"description": "Your channels, or the projects in one channel.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"enum": [
"channels",
"projects"
],
"type": "string",
"description": "channels: your channels; projects: the projects in channel_id"
},
"channel_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "projects: the channel"
}
}
},
"annotations": {
"title": "Read channels and projects",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Create a channel or a project, or change a project's title, brief or video format. A new project takes its channel's style; a channel with no style needs one (style_edit action=create) before anything is generated. Share the returned web_url so the user can follow along.
| Parameter | Type | Description |
|---|---|---|
| name | any | create_channel: the channel name |
| title | any | The project title |
| action * | string | create_channel: name, optional description; create_project: channel_id, title, optional description, video_format; update_project: project_id and any of title, description, video_format |
| channel_id | any | create_project: its channel |
| project_id | any | Project id |
| description | any | A channel: what it is about. A project: the brief, what the video is about; it seeds the script, so make it specific |
| video_format | any | landscape (16:9, the default) or portrait (9:16: Shorts, Reels, TikTok); fixed once a storyboard exists |
{
"name": "projects_edit",
"title": "Edit channels and projects",
"description": "Create a channel or a project, or change a project's title, brief or\nvideo format. A new project takes its channel's style; a channel with no\nstyle needs one (style_edit action=create) before anything is\ngenerated. Share the returned web_url so the user can follow along.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "create_channel: the channel name"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The project title"
},
"action": {
"enum": [
"create_channel",
"create_project",
"update_project"
],
"type": "string",
"description": "create_channel: name, optional description; create_project: channel_id, title, optional description, video_format; update_project: project_id and any of title, description, video_format"
},
"channel_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "create_project: its channel"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "A channel: what it is about. A project: the brief, what the video is about; it seeds the script, so make it specific"
},
"video_format": {
"anyOf": [
{
"enum": [
"landscape",
"portrait"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "landscape (16:9, the default) or portrait (9:16: Shorts, Reels, TikTok); fixed once a storyboard exists"
}
}
},
"annotations": {
"title": "Edit channels and projects",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}get: the channel style: its references, its fields (art_style, narrative_style, director_style, text_style, any added; script_prompt on request), the summary analysis wrote for each, and templates, the character and environment template images (null: not rendered; a URL: it exists, so view_image it rather than render it again). inputs_stale: the references changed since the last analysis (offer style_generate action=analyze). templates_stale: the art style or its image references changed since the templates were rendered (offer to render them again). presets: the preset catalog, one list per axis (art_style, narrative_style, director_style), with labels, descriptions and, for art presets, preview images. Let the user pick one per axis.
| Parameter | Type | Description |
|---|---|---|
| action * | string | get: the channel style (channel_id or project_id); presets: the preset catalog |
| channel_id | any | get: the channel (or pass project_id) |
| project_id | any | Project id |
| include_script_prompt | boolean | get: include the long script_prompt |
{
"name": "style_read",
"title": "Read the channel style",
"description": "get: the channel style: its references, its fields (art_style,\nnarrative_style, director_style, text_style, any added; script_prompt on\nrequest), the summary analysis wrote for each, and templates, the\ncharacter and environment template images (null: not rendered; a URL:\nit exists, so view_image it rather than render it again).\ninputs_stale: the references changed since the last analysis (offer\nstyle_generate action=analyze). templates_stale: the art style or its\nimage references changed since the templates were rendered (offer to render them again).\n\npresets: the preset catalog, one list per axis (art_style,\nnarrative_style, director_style), with labels, descriptions and, for art\npresets, preview images. Let the user pick one per axis.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"enum": [
"get",
"presets"
],
"type": "string",
"description": "get: the channel style (channel_id or project_id); presets: the preset catalog"
},
"channel_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "get: the channel (or pass project_id)"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"include_script_prompt": {
"type": "boolean",
"default": false,
"description": "get: include the long script_prompt"
}
}
},
"annotations": {
"title": "Read the channel style",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Create or change the channel style (one per channel, used by all its projects). create: offer the user two real options, never invented ones. (a) References (best): YouTube links of their channel or of videos whose look they like, or a written description. Analysis starts at once and writes the fields: wait with get_status channel_id wait=true, then render both template images (style_generate action=template). A reference informs every axis, narrative included; for its look only, give it contributes_to ["art_style"]. (b) Presets: one per axis, all three; instant, and the art preset brings its template images. Presets and references don't mix. update_fields: replace fields' text; it never starts an analysis (an analysis rewrites art_style, narrative_style, director_style and text_style). Those four and script_prompt can't be removed, every field needs text, and summaries are written only by analysis. Real photos and B-roll are turned on by the literal `@real-media` tag in director_style, with prose on when and how much; remove it to turn them off. update_references: replace the references, fields untouched (inputs_stale turns true). File references can only be added in the app.
| Parameter | Type | Description |
|---|---|---|
| name | any | create: the style name |
| action * | string | create: name, and references or presets; update_fields: fields; update_references: references |
| fields | any | update_fields: {key: "new text"} for the keys you change; {key: null} removes a key you added |
| presets | any | create: {"art_style": id, "narrative_style": id, "director_style": id} from style_read action=presets |
| channel_id * | string | The channel whose style this is |
| references | any | [{"input_type": "youtube" | "text", "value": "<link or description>", "contributes_to": ["art_style", ...]?}]. A youtube value is a video link, or a channel link or @handle. update_references: the COMPLETE list in order; copy kept entries from style_read verbatim. |
{
"name": "style_edit",
"title": "Edit the channel style",
"description": "Create or change the channel style (one per channel, used by all its\nprojects).\n\ncreate: offer the user two real options, never invented ones. (a)\nReferences (best): YouTube links of their channel or of videos whose\nlook they like, or a written description. Analysis starts at once and\nwrites the fields: wait with get_status channel_id wait=true, then\nrender both template images (style_generate action=template). A\nreference informs every axis, narrative included; for its look only,\ngive it contributes_to [\"art_style\"]. (b) Presets: one per axis, all\nthree; instant, and the art preset brings its template images. Presets\nand references don't mix.\n\nupdate_fields: replace fields' text; it never starts an analysis (an\nanalysis rewrites art_style, narrative_style, director_style and\ntext_style). Those four and script_prompt can't be removed, every field\nneeds text, and summaries are written only by analysis. Real photos and\nB-roll are turned on by the literal `@real-media` tag in director_style,\nwith prose on when and how much; remove it to turn them off.\n\nupdate_references: replace the references, fields untouched\n(inputs_stale turns true). File references can only be added in the\napp.",
"inputSchema": {
"type": "object",
"required": [
"action",
"channel_id"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "create: the style name"
},
"action": {
"enum": [
"create",
"update_fields",
"update_references"
],
"type": "string",
"description": "create: name, and references or presets; update_fields: fields; update_references: references"
},
"fields": {
"anyOf": [
{
"type": "object",
"additionalProperties": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
]
}
},
{
"type": "null"
}
],
"description": "update_fields: {key: \"new text\"} for the keys you change; {key: null} removes a key you added"
},
"presets": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "create: {\"art_style\": id, \"narrative_style\": id, \"director_style\": id} from style_read action=presets"
},
"channel_id": {
"type": "string",
"description": "The channel whose style this is"
},
"references": {
"anyOf": [
{
"type": "array",
"items": {
"type": "object",
"additionalProperties": true
}
},
{
"type": "null"
}
],
"description": "[{\"input_type\": \"youtube\" | \"text\", \"value\": \"<link or description>\", \"contributes_to\": [\"art_style\", ...]?}]. A youtube value is a video link, or a channel link or @handle. update_references: the COMPLETE list in order; copy kept entries from style_read verbatim."
}
}
},
"annotations": {
"title": "Edit the channel style",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}analyze: read the references again and rewrite art_style, narrative_style, director_style and text_style, replacing hand edits. template: render one of the style's two template images. Reference images render on them (characters on the character template, environments and objects on the environment one) and segment images fall back on them, so finish both before any reference image. An existing one is refused unless replace=true: replacing it changes the look of everything rendered after.
| Parameter | Type | Description |
|---|---|---|
| model | any | Model id (get_generation_options); omit for the saved choice |
| action * | string | analyze; template: template_type |
| replace | boolean | template: true only when the user asked for a new image (or agreed to render a stale one again) |
| settings | any | Model settings: keys of its settings_schema |
| channel_id * | string | The channel whose style this is |
| template_type | any | template: which template image; run once for each |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "style_generate",
"title": "Generate for the channel style",
"description": "analyze: read the references again and rewrite art_style,\nnarrative_style, director_style and text_style, replacing hand edits.\n\ntemplate: render one of the style's two template images. Reference\nimages render on them (characters on the character template,\nenvironments and objects on the environment one) and segment images\nfall back on them, so finish both before any reference image. An\nexisting one is refused unless replace=true: replacing it changes the\nlook of everything rendered after.",
"inputSchema": {
"type": "object",
"required": [
"action",
"channel_id"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"action": {
"enum": [
"analyze",
"template"
],
"type": "string",
"description": "analyze; template: template_type"
},
"replace": {
"type": "boolean",
"default": false,
"description": "template: true only when the user asked for a new image (or agreed to render a stale one again)"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"channel_id": {
"type": "string",
"description": "The channel whose style this is"
},
"template_type": {
"anyOf": [
{
"enum": [
"character",
"environment"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "template: which template image; run once for each"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Generate for the channel style",
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": true
}
}The active script, its versions, and the script settings (script_target_minutes, voice_mix, visual concept). Show the script to the user before Analyze Script.
| Parameter | Type | Description |
|---|---|---|
| project_id * | string | Project id |
{
"name": "script_read",
"title": "Read the script",
"description": "The active script, its versions, and the script settings\n(script_target_minutes, voice_mix, visual concept). Show the script to\nthe user before Analyze Script.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "string",
"description": "Project id"
}
}
},
"annotations": {
"title": "Read the script",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Change the script or its settings; only revise spends credits. save: replace the active version's text (the old text is lost: show the user the current script first), then run Analyze Script. Notation, never read aloud: `[SCENE: <visual direction>]` as its own paragraph directs the storyboard for the narration after it, until the next one, over the director style. `<break time="1.5s" />` is the only thing that makes the voice pause (about 0.5s between thoughts, 1.0s between sections; one tag with the total, never two in a row). A paragraph starting `Name: "..."` is that character's dialogue. A delivery cue in square brackets inside a line (`[laughs]`, `[sighs]`, `[whispers]`) shapes how it is said; keep it inline, never on its own line. MiniMax performs sounds such as laughs, sighs, breathes, gasps and coughs and drops other cues. activate_version: switch to another version (each generated script is one). revise: an AI rewrite of a passage or the whole script in the narrative voice; returns revised_text without saving it: splice it in and save.
| Parameter | Type | Description |
|---|---|---|
| action * | string | save: content; activate_version: script_id; revise: instruction, optional selected_text; settings: script_target_minutes and/or voice_mix; set_concept: visual_concept |
| content | any | save: the full script text |
| script_id | any | activate_version: a version id from script_read |
| voice_mix | any | settings: narration versus character dialogue |
| project_id * | string | Project id |
| instruction | any | revise: what to change, e.g. "make the intro punchier" |
| selected_text | any | revise: the exact passage to rewrite; omit for the whole script |
| visual_concept | any | set_concept: how the video looks |
| script_target_minutes | any | settings: length of the next generated script, in minutes |
{
"name": "script_edit",
"title": "Edit the script",
"description": "Change the script or its settings; only revise spends credits.\n\nsave: replace the active version's text (the old text is lost: show the\nuser the current script first), then run Analyze Script. Notation, never\nread aloud: `[SCENE: <visual direction>]` as its own paragraph directs\nthe storyboard for the narration after it, until the next one, over the\ndirector style. `<break time=\"1.5s\" />` is the only thing that makes the\nvoice pause (about 0.5s between thoughts, 1.0s between sections; one tag\nwith the total, never two in a row). A paragraph starting `Name: \"...\"`\nis that character's dialogue. A delivery cue in square brackets inside\na line (`[laughs]`, `[sighs]`, `[whispers]`) shapes how it is said; keep\nit inline, never on its own line. MiniMax performs sounds such as\nlaughs, sighs, breathes, gasps and coughs and drops other cues.\n\nactivate_version: switch to another version (each generated script is\none). revise: an AI rewrite of a passage or the whole script in the\nnarrative voice; returns revised_text without saving it: splice it in\nand save.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id"
],
"properties": {
"action": {
"enum": [
"save",
"activate_version",
"revise",
"settings",
"set_concept"
],
"type": "string",
"description": "save: content; activate_version: script_id; revise: instruction, optional selected_text; settings: script_target_minutes and/or voice_mix; set_concept: visual_concept"
},
"content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "save: the full script text"
},
"script_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "activate_version: a version id from script_read"
},
"voice_mix": {
"anyOf": [
{
"enum": [
"narrator_only",
"narrator_led",
"balanced",
"character_led"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "settings: narration versus character dialogue"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"instruction": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "revise: what to change, e.g. \"make the intro punchier\""
},
"selected_text": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "revise: the exact passage to rewrite; omit for the whole script"
},
"visual_concept": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_concept: how the video looks"
},
"script_target_minutes": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "settings: length of the next generated script, in minutes"
}
}
},
"annotations": {
"title": "Edit the script",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}generate: write the script from the brief and the narrative style; each run is a new version (review it with script_read). analyze (Analyze Script): find the script's characters, environments and objects (including any named only in `[SCENE: ...]` directions) and split it into voice blocks. Existing assets are kept as they are (description, reference image, voice) and new ones added; assets the script no longer names stay until the user deletes them. Review with assets_read.
| Parameter | Type | Description |
|---|---|---|
| model | any | Model id (get_generation_options); omit for the saved choice |
| action * | string | generate: write the script; analyze: Analyze Script |
| settings | any | Model settings: keys of its settings_schema |
| project_id * | string | Project id |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "script_generate",
"title": "Generate the script or analyze it",
"description": "generate: write the script from the brief and the narrative style;\neach run is a new version (review it with script_read).\n\nanalyze (Analyze Script): find the script's characters, environments\nand objects (including any named only in `[SCENE: ...]` directions) and\nsplit it into voice blocks. Existing assets are kept as they are\n(description, reference image, voice) and new ones added; assets the\nscript no longer names stay until the user deletes them. Review with\nassets_read.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"action": {
"enum": [
"generate",
"analyze"
],
"type": "string",
"description": "generate: write the script; analyze: Analyze Script"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Generate the script or analyze it",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}The project's characters, environments and objects, each with its description (what every render follows), reference_image (null: not rendered; view_image it), its image's status (as storyboard_read's: stale when its description changed since it rendered) and, for characters, voice_id. Each needs a reference image before the voiceover.
| Parameter | Type | Description |
|---|---|---|
| asset_type | any | Only this kind |
| project_id * | string | Project id |
{
"name": "assets_read",
"title": "Read assets",
"description": "The project's characters, environments and objects, each with its\ndescription (what every render follows), reference_image (null: not\nrendered; view_image it), its image's status (as storyboard_read's:\nstale when its description changed since it rendered) and, for\ncharacters, voice_id. Each needs a reference image before the voiceover.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"asset_type": {
"anyOf": [
{
"enum": [
"character",
"environment",
"object"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "Only this kind"
},
"project_id": {
"type": "string",
"description": "Project id"
}
}
},
"annotations": {
"title": "Read assets",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Add a character, environment or object that Analyze Script missed, or rewrite one's description. After a description change, render its reference image again (assets_generate asset_ids).
| Parameter | Type | Description |
|---|---|---|
| name | any | The name the script uses for it |
| action * | string | create: project_id, asset_type, name, optional description; update: asset_id and description |
| asset_id | any | update: the asset id |
| asset_type | any | create: the kind |
| project_id | any | Project id |
| description | any | What it looks like; every render follows it, so be specific |
{
"name": "assets_edit",
"title": "Edit assets",
"description": "Add a character, environment or object that Analyze Script missed,\nor rewrite one's description. After a description change, render its\nreference image again (assets_generate asset_ids).",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The name the script uses for it"
},
"action": {
"enum": [
"create",
"update"
],
"type": "string",
"description": "create: project_id, asset_type, name, optional description; update: asset_id and description"
},
"asset_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "update: the asset id"
},
"asset_type": {
"anyOf": [
{
"enum": [
"character",
"environment",
"object"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "create: the kind"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "What it looks like; every render follows it, so be specific"
}
}
},
"annotations": {
"title": "Edit assets",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Render reference images, which keep each character, environment and object looking the same in every segment. Needs both style template images. Without asset_ids it renders every asset with none, skipping ones already rendering, so a repeat never bills twice. Afterwards, view_image them to check likeness.
| Parameter | Type | Description |
|---|---|---|
| model | any | Model id (get_generation_options); omit for the saved choice |
| dry_run | boolean | Return the count and credit estimate; start nothing |
| settings | any | Model settings: keys of its settings_schema |
| asset_ids | any | Assets to render, again if they have one; omit for every asset without a reference image |
| project_id * | string | Project id |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "assets_generate",
"title": "Generate reference images",
"description": "Render reference images, which keep each character, environment and\nobject looking the same in every segment. Needs both style template\nimages. Without asset_ids it renders every asset with none, skipping\nones already rendering, so a repeat never bills twice. Afterwards,\nview_image them to check likeness.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"dry_run": {
"type": "boolean",
"default": false,
"description": "Return the count and credit estimate; start nothing"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"asset_ids": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"description": "Assets to render, again if they have one; omit for every asset without a reference image"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Generate reference images",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}voices: one engine's voice ids, labels and preview audio, as {groups, voices}. blocks: the voice blocks (narration and dialogue) with their speaker, voice_id (the speaker's voice), audio and any `[SCENE: ...]` direction over them (never spoken), as {blocks, total_duration_ms, all_complete}.
| Parameter | Type | Description |
|---|---|---|
| group | any | voices: one catalog group; each engine has its own (see groups). Filter the large ElevenLabs catalog. |
| action * | string | voices: the voice catalog for provider; blocks: the project's voice blocks |
| provider | string | voices: the voice engine (the project's voice_tts_provider) |
| project_id | any | Project id |
| include_subtitle_data | boolean | blocks: include word-level timings (bulky) |
{
"name": "voiceover_read",
"title": "Read voices and voice blocks",
"description": "voices: one engine's voice ids, labels and preview audio, as\n{groups, voices}. blocks: the voice blocks (narration and dialogue) with\ntheir speaker, voice_id (the speaker's voice), audio and any\n`[SCENE: ...]` direction over them (never spoken), as {blocks,\ntotal_duration_ms, all_complete}.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"group": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "voices: one catalog group; each engine has its own (see groups). Filter the large ElevenLabs catalog."
},
"action": {
"enum": [
"voices",
"blocks"
],
"type": "string",
"description": "voices: the voice catalog for provider; blocks: the project's voice blocks"
},
"provider": {
"enum": [
"minimax",
"elevenlabs"
],
"type": "string",
"default": "minimax",
"description": "voices: the voice engine (the project's voice_tts_provider)"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"include_subtitle_data": {
"type": "boolean",
"default": false,
"description": "blocks: include word-level timings (bulky)"
}
}
},
"annotations": {
"title": "Read voices and voice blocks",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Voices and voice blocks; free. set_voice: the narrator's or a character's voice; every speaker needs one before the voiceover. rescan_blocks: split the active script into voice blocks again after an edit, assets untouched; blocks whose words are unchanged keep their audio. settings: the voice engine, narrator speed and language.
| Parameter | Type | Description |
|---|---|---|
| action * | string | set_voice: speaker, voice_id; rescan_blocks; settings: voice_tts_provider, narrator_speed and/or language |
| speaker | any | set_voice: "narrator", or a character's name |
| language | any | settings: the script's language as an ISO 639-1 code; Analyze Script detects it and overwrites it on every run |
| voice_id | any | set_voice: a voice id from voiceover_read action=voices |
| project_id * | string | Project id |
| narrator_speed | any | settings: speaking rate, 0.5-2.0 (default 1.0); pauses come only from `<break>` tags |
| voice_tts_provider | any | settings: the voice engine |
{
"name": "voiceover_edit",
"title": "Edit voices and voice blocks",
"description": "Voices and voice blocks; free. set_voice: the narrator's or a\ncharacter's voice; every speaker needs one before the voiceover.\nrescan_blocks: split the active script into voice blocks again after an\nedit, assets untouched; blocks whose words are unchanged keep their\naudio. settings: the voice engine, narrator speed and language.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id"
],
"properties": {
"action": {
"enum": [
"set_voice",
"rescan_blocks",
"settings"
],
"type": "string",
"description": "set_voice: speaker, voice_id; rescan_blocks; settings: voice_tts_provider, narrator_speed and/or language"
},
"speaker": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_voice: \"narrator\", or a character's name"
},
"language": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "settings: the script's language as an ISO 639-1 code; Analyze Script detects it and overwrites it on every run"
},
"voice_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_voice: a voice id from voiceover_read action=voices"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"narrator_speed": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "settings: speaking rate, 0.5-2.0 (default 1.0); pauses come only from `<break>` tags"
},
"voice_tts_provider": {
"anyOf": [
{
"enum": [
"minimax",
"elevenlabs"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "settings: the voice engine"
}
}
},
"annotations": {
"title": "Edit voices and voice blocks",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Generate voice block audio. Every speaker needs a voice first, and every asset a reference image. Without voice_block_ids it fills every block with no audio, skipping ones already generating. A model must match the project's voice engine. An existing storyboard retimes to the new audio on its own.
| Parameter | Type | Description |
|---|---|---|
| model | any | Model id (get_generation_options); omit for the saved choice |
| dry_run | boolean | Return the count and credit estimate; start nothing |
| settings | any | Model settings: keys of its settings_schema |
| project_id * | string | Project id |
| voice_block_ids | any | Blocks to generate, again if they have audio; omit for every block without audio |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "voiceover_generate",
"title": "Generate the voiceover",
"description": "Generate voice block audio. Every speaker needs a voice first, and\nevery asset a reference image. Without voice_block_ids it fills every\nblock with no audio, skipping ones already generating. A model must\nmatch the project's voice engine. An existing storyboard retimes to the\nnew audio on its own.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"dry_run": {
"type": "boolean",
"default": false,
"description": "Return the count and credit estimate; start nothing"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"voice_block_ids": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"description": "Blocks to generate, again if they have audio; omit for every block without audio"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Generate the voiceover",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}segments: {total, offset, returned, segments}. Each segment has its segment_number (the handle segment tools take), kind (image, clip, talking head, real photo, B-roll or overlay segment), narration, duration, direction, image_prompt, video_prompt (the motion when animated), media_queries (searches for a real photo or B-roll), the characters, environments and objects it shows, continues_from_segment (its image continues that earlier segment's image) and its assets. segment_assets: {segment_number, assets}: its image, clip, real photos, overlays and sound effects, each with kind, status, prompt, model, earlier_renders (what a rollback can restore) and public_url (for view_image).
| Parameter | Type | Description |
|---|---|---|
| limit | integer | segments: how many; 0 returns all. Long videos have 100+, so page. |
| action * | string | segments: the storyboard, paged; segment_assets: one segment's assets (segment_number) |
| offset | integer | segments: first to return, 0-based |
| project_id * | string | Project id |
| segment_number | any | Segment number (1-based, from storyboard_read) |
{
"name": "storyboard_read",
"title": "Read the storyboard",
"description": "segments: {total, offset, returned, segments}. Each segment has its\nsegment_number (the handle segment tools take), kind (image, clip,\ntalking head, real photo, B-roll or overlay segment), narration,\nduration, direction, image_prompt, video_prompt (the motion when\nanimated), media_queries (searches for a real photo or B-roll), the\ncharacters, environments and objects it shows, continues_from_segment\n(its image continues that earlier segment's image) and its assets.\n\nsegment_assets: {segment_number, assets}: its image, clip, real photos,\noverlays and sound effects, each with kind, status, prompt, model,\nearlier_renders (what a rollback can restore) and public_url (for\nview_image).",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 0,
"description": "segments: how many; 0 returns all. Long videos have 100+, so page."
},
"action": {
"enum": [
"segments",
"segment_assets"
],
"type": "string",
"description": "segments: the storyboard, paged; segment_assets: one segment's assets (segment_number)"
},
"offset": {
"type": "integer",
"default": 0,
"description": "segments: first to return, 0-based"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"segment_number": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Segment number (1-based, from storyboard_read)"
}
}
},
"annotations": {
"title": "Read the storyboard",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Storyboard settings, used by the next storyboard run.
| Parameter | Type | Description |
|---|---|---|
| action * | string | settings: sfx_level |
| sfx_level * | string | How many sound effects the storyboard plans |
| project_id * | string | Project id |
{
"name": "storyboard_edit",
"title": "Edit storyboard settings",
"description": "Storyboard settings, used by the next storyboard run.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id",
"sfx_level"
],
"properties": {
"action": {
"type": "string",
"const": "settings",
"description": "settings: sfx_level"
},
"sfx_level": {
"enum": [
"none",
"minimal",
"frequent"
],
"type": "string",
"description": "How many sound effects the storyboard plans"
},
"project_id": {
"type": "string",
"description": "Project id"
}
}
},
"annotations": {
"title": "Edit storyboard settings",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Plan the storyboard: every segment, its timing, image and motion prompts, overlays and continuations, following the channel style and any `[SCENE: ...]` directions. Needs the finished voiceover (its timing drives the cuts). It plans images, plus real photos and B-roll when the director style has the `@real-media` tag; clips come later, by animating rendered images. Running it again replaces the whole plan, edits included. The longest step (several minutes): get_status wait=true, repeatedly.
| Parameter | Type | Description |
|---|---|---|
| model | any | Model id (get_generation_options); omit for the saved choice |
| settings | any | Model settings: keys of its settings_schema |
| project_id * | string | Project id |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "storyboard_generate",
"title": "Generate the storyboard",
"description": "Plan the storyboard: every segment, its timing, image and motion\nprompts, overlays and continuations, following the channel style and\nany `[SCENE: ...]` directions. Needs the finished voiceover (its timing\ndrives the cuts). It plans images, plus real photos and B-roll when the\ndirector style has the `@real-media` tag; clips come later, by animating\nrendered images. Running it again replaces the whole plan, edits\nincluded. The longest step (several minutes): get_status wait=true,\nrepeatedly.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Generate the storyboard",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Change one segment without losing renders. Returns the changed segments. set_prompts: write prompts verbatim, no AI rewrite. The renders stay as they are: render the segment again to apply the new prompts. set_continuation: make this segment's image continue an earlier one's (same composition, only the change); render the image again. rollback: restore one of the last 5 renders of the image or clip; the current one takes its place, so it can be undone, and the prompt editor's model stays as it is. split: cut into 2-4 parts; every part keeps the prompts and renders (copies, so each part can be changed and rendered on its own), and nothing is rendered or rewritten. Later segments renumber: read the storyboard again before more edits.
| Parameter | Type | Description |
|---|---|---|
| what | any | rollback: restore the image or the clip |
| index | integer | rollback: which earlier render, 0 = the latest |
| action * | string | set_prompts: image_prompt, video_prompt and/or media_queries; set_continuation: continues_from; rollback: what, optional index; split: offsets_ms |
| offsets_ms | any | split: 1-3 ascending cut points, in ms from the segment's start; word timings: voiceover_read action=blocks include_subtitle_data=true |
| project_id * | string | Project id |
| image_prompt | any | set_prompts: the image prompt |
| video_prompt | any | set_prompts: the motion used when the image is animated |
| media_queries | any | set_prompts: searches for a real photo or B-roll |
| continues_from | any | set_continuation: an EARLIER segment number; 0 clears the link |
| segment_number * | integer | Segment number (1-based, from storyboard_read) |
{
"name": "segment_edit",
"title": "Edit a segment",
"description": "Change one segment without losing renders. Returns the changed\nsegments.\n\nset_prompts: write prompts verbatim, no AI rewrite. The renders stay as\nthey are: render the segment again to apply the new prompts.\nset_continuation: make this segment's image continue an earlier one's\n(same composition, only the change); render the image again.\nrollback: restore one of the last 5 renders of the image or clip; the\ncurrent one takes its place, so it can be undone, and the prompt\neditor's model stays as it is. split: cut into 2-4 parts; every part\nkeeps the prompts and renders (copies, so each part can be changed and\nrendered on its own), and nothing is rendered or rewritten. Later\nsegments renumber: read the storyboard again before more edits.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id",
"segment_number"
],
"properties": {
"what": {
"anyOf": [
{
"enum": [
"image",
"clip"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "rollback: restore the image or the clip"
},
"index": {
"type": "integer",
"default": 0,
"description": "rollback: which earlier render, 0 = the latest"
},
"action": {
"enum": [
"set_prompts",
"set_continuation",
"rollback",
"split"
],
"type": "string",
"description": "set_prompts: image_prompt, video_prompt and/or media_queries; set_continuation: continues_from; rollback: what, optional index; split: offsets_ms"
},
"offsets_ms": {
"anyOf": [
{
"type": "array",
"items": {
"type": "integer"
}
},
{
"type": "null"
}
],
"description": "split: 1-3 ascending cut points, in ms from the segment's start; word timings: voiceover_read action=blocks include_subtitle_data=true"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"image_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_prompts: the image prompt"
},
"video_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "set_prompts: the motion used when the image is animated"
},
"media_queries": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"description": "set_prompts: searches for a real photo or B-roll"
},
"continues_from": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "set_continuation: an EARLIER segment number; 0 clears the link"
},
"segment_number": {
"type": "integer",
"description": "Segment number (1-based, from storyboard_read)"
}
}
},
"annotations": {
"title": "Edit a segment",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Change what a segment is. No render is ever lost: what a change replaces goes to the bin. combine: merge with a neighboring segment. The kept segment's prompts and renders stay over the combined length (a clip too short plays over its image; B-roll too short is refused); the other's go to the bin. Its sound effects and overlays join the kept segment. change_type: to an image, real photo or B-roll (both fetched). Clips and talking heads come from render action=animate. keep_image turns a clip back into its image, keeping the render. The prompts carry over unchanged; render the segment again. A real photo or B-roll takes the searches it had before; one that had none gets them written by a small AI step in the background, which writes only its searches and spends credits (get_status wait=true); it renders once that finishes. rewrite: an AI rewrite of the prompts from feedback, in the background: a small AI step that spends credits (get_status wait=true); render the image and clip again after. For exact text, use segment_edit set_prompts. Sound effects and overlays always survive; change an overlay's text with editor_edit scene_note. Later segments may renumber: read the storyboard again.
| Parameter | Type | Description |
|---|---|---|
| to | any | change_type: the new kind |
| keep | string | combine: whose prompts and renders survive |
| action * | string | combine: with_segment_number, optional keep; change_type: to, optional keep_image; rewrite: feedback |
| feedback | any | rewrite: what to change, e.g. "make this a close-up" |
| keep_image | boolean | change_type from a clip to image: keep the rendered image |
| project_id * | string | Project id |
| segment_number * | integer | Segment number (1-based, from storyboard_read) |
| with_segment_number | any | combine: the neighboring segment |
{
"name": "segment_restructure",
"title": "Restructure a segment",
"description": "Change what a segment is. No render is ever lost: what a change\nreplaces goes to the bin.\n\ncombine: merge with a neighboring segment. The kept segment's prompts\nand renders stay over the combined length (a clip too short plays over\nits image; B-roll too short is refused); the other's go to the bin. Its\nsound effects and overlays join the kept segment.\n\nchange_type: to an image, real photo or B-roll (both fetched). Clips\nand talking heads come from render action=animate. keep_image turns a\nclip back into its image, keeping the render. The prompts carry over\nunchanged; render the segment again. A real photo or B-roll takes the\nsearches it had before; one that had none gets them written by a small\nAI step in the background, which writes only its searches and spends\ncredits (get_status wait=true); it renders once that finishes.\n\nrewrite: an AI rewrite of the prompts from feedback, in the background:\na small AI step that spends credits (get_status wait=true); render the\nimage and clip again after. For exact text, use segment_edit\nset_prompts.\n\nSound effects and overlays always survive; change an overlay's text\nwith editor_edit scene_note. Later segments may renumber: read the\nstoryboard again.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id",
"segment_number"
],
"properties": {
"to": {
"anyOf": [
{
"enum": [
"image",
"real_photo",
"b_roll"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "change_type: the new kind"
},
"keep": {
"enum": [
"this",
"other"
],
"type": "string",
"default": "this",
"description": "combine: whose prompts and renders survive"
},
"action": {
"enum": [
"combine",
"change_type",
"rewrite"
],
"type": "string",
"description": "combine: with_segment_number, optional keep; change_type: to, optional keep_image; rewrite: feedback"
},
"feedback": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "rewrite: what to change, e.g. \"make this a close-up\""
},
"keep_image": {
"type": "boolean",
"default": false,
"description": "change_type from a clip to image: keep the rendered image"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"segment_number": {
"type": "integer",
"description": "Segment number (1-based, from storyboard_read)"
},
"with_segment_number": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "combine: the neighboring segment"
}
}
},
"annotations": {
"title": "Restructure a segment",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Render segment images and clips, the biggest spend in the video: always run it with dry_run=true first and get the user's yes on the estimate. generate: without segment_numbers, everything not yet rendered (items rendering are skipped); with them, those segments, finished renders included, e.g. the first minute before the whole video. Overrides need segment_numbers and what=images or what=clips. animate: turn one segment's rendered image into a clip; animate only images worth motion. dry_run quotes the default clip or talking head model. A refused render leaves the segment as it was; to go back to the image, segment_restructure change_type to=image keep_image=true. Check renders with storyboard_read action=segment_assets and view_image.
| Parameter | Type | Description |
|---|---|---|
| what | string | generate: images (everything but clips: images, overlay segments, real photos, B-roll), clips, or all |
| model | any | Model id (get_generation_options); omit for the saved choice |
| action * | string | generate: optional segment_numbers, what; animate: segment_number, optional talking_head |
| dry_run | boolean | Return the count and credit estimate; start nothing |
| settings | any | Model settings: keys of its settings_schema |
| project_id * | string | Project id |
| talking_head | boolean | animate: true for a talking head (the person in the image speaks the narration with lip sync, billed on the segment's full length); false for a clip |
| segment_number | any | Segment number (1-based, from storyboard_read) |
| segment_numbers | any | generate: only these segments, finished ones included; omit for everything not yet rendered |
| editable_sections | any | Template prompt section overrides, keyed by section id |
{
"name": "render",
"title": "Render segments",
"description": "Render segment images and clips, the biggest spend in the video:\nalways run it with dry_run=true first and get the user's yes on the\nestimate.\n\ngenerate: without segment_numbers, everything not yet rendered (items\nrendering are skipped); with them, those segments, finished renders\nincluded, e.g. the first minute before the whole video. Overrides need\nsegment_numbers and what=images or what=clips.\n\nanimate: turn one segment's rendered image into a clip; animate only\nimages worth motion. dry_run quotes the default clip or talking head\nmodel. A refused render leaves the segment as it was; to go back to the\nimage, segment_restructure change_type to=image keep_image=true.\n\nCheck renders with storyboard_read action=segment_assets and\nview_image.",
"inputSchema": {
"type": "object",
"required": [
"action",
"project_id"
],
"properties": {
"what": {
"enum": [
"images",
"clips",
"all"
],
"type": "string",
"default": "all",
"description": "generate: images (everything but clips: images, overlay segments, real photos, B-roll), clips, or all"
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Model id (get_generation_options); omit for the saved choice"
},
"action": {
"enum": [
"generate",
"animate"
],
"type": "string",
"description": "generate: optional segment_numbers, what; animate: segment_number, optional talking_head"
},
"dry_run": {
"type": "boolean",
"default": false,
"description": "Return the count and credit estimate; start nothing"
},
"settings": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Model settings: keys of its settings_schema"
},
"project_id": {
"type": "string",
"description": "Project id"
},
"talking_head": {
"type": "boolean",
"default": false,
"description": "animate: true for a talking head (the person in the image speaks the narration with lip sync, billed on the segment's full length); false for a clip"
},
"segment_number": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Segment number (1-based, from storyboard_read)"
},
"segment_numbers": {
"anyOf": [
{
"type": "array",
"items": {
"type": "integer"
}
},
{
"type": "null"
}
],
"description": "generate: only these segments, finished ones included; omit for everything not yet rendered"
},
"editable_sections": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "Template prompt section overrides, keyed by section id"
}
}
},
"annotations": {
"title": "Render segments",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}scenes: the editor timeline, one scene per segment, as {total, offset, returned, scenes}. music: {tracks}, timed in seconds. audio_library: tracks to add with editor_edit; when nothing matches, it lists the library's moods and genres.
| Parameter | Type | Description |
|---|---|---|
| mood | any | audio_library: a mood tag |
| genre | any | audio_library: a genre tag |
| limit | integer | scenes: how many; 0 returns all |
| action * | string | scenes: the timeline (project_id); music: the project's music tracks (project_id); audio_library: music and sound effects to add |
| offset | integer | scenes: first to return, 0-based |
| search | any | audio_library: free text |
| category | any | audio_library: music or sfx (sound effects); omit for both |
| project_id | any | Project id |
| include_composition | boolean | scenes: include each scene's full layer JSON (bulky: page it) |
{
"name": "editor_read",
"title": "Read the editor",
"description": "scenes: the editor timeline, one scene per segment, as {total,\noffset, returned, scenes}. music: {tracks}, timed in seconds. audio_library: tracks to\nadd with editor_edit; when nothing matches, it lists the library's moods\nand genres.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"mood": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "audio_library: a mood tag"
},
"genre": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "audio_library: a genre tag"
},
"limit": {
"type": "integer",
"default": 0,
"description": "scenes: how many; 0 returns all"
},
"action": {
"enum": [
"scenes",
"music",
"audio_library"
],
"type": "string",
"description": "scenes: the timeline (project_id); music: the project's music tracks (project_id); audio_library: music and sound effects to add"
},
"offset": {
"type": "integer",
"default": 0,
"description": "scenes: first to return, 0-based"
},
"search": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "audio_library: free text"
},
"category": {
"anyOf": [
{
"enum": [
"music",
"sfx"
],
"type": "string"
},
{
"type": "null"
}
],
"description": "audio_library: music or sfx (sound effects); omit for both"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"include_composition": {
"type": "boolean",
"default": false,
"description": "scenes: include each scene's full layer JSON (bulky: page it)"
}
}
},
"annotations": {
"title": "Read the editor",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Polish the video in the editor; changes show in the next export. scene_note: edit one scene with a note (move, restyle, add or remove layers and overlays, change the text of a lower third, title card or callout, change motion); spends credits. Returns the changes and skipped_mutations: edits that didn't land (applied=false) or landed differently than asked (applied=true), each with a reason; check them. Scene lengths follow the narration; the image, clip and voiceover layers can't be removed. project_note: a note for the whole video, applied to up to 10 scenes per call; spends credits. captions: merge caption settings. add_sfx: attach a sound effect to a segment. add_music / update_music: background music timed in seconds; a track's duration follows from its trim.
| Parameter | Type | Description |
|---|---|---|
| loop | any | Loop the music under the whole video |
| name | any | The music track's name |
| action * | string | scene_note: segment_number, message; project_note: message; captions: caption_config; add_sfx: segment_number, library_track_id; add_music: library_track_id, optional name, volume, loop, start_seconds; update_music: track_id and any of name, volume, loop, start_seconds, trim_start_seconds, trim_end_… |
| volume | any | Music volume 0-1; the 0.12 default sits under the narration, so raise it only if asked |
| message | any | The note in plain words, e.g. "move the caption to the top" |
| track_id | any | update_music: a track id from editor_read action=music |
| project_id | any | Project id |
| start_seconds | any | Where the music starts in the video, in seconds |
| caption_config | any | captions: keys to merge into the caption settings (get_status shows them) |
| segment_number | any | Segment number (1-based, from storyboard_read) |
| library_track_id | any | A track id from editor_read action=audio_library |
| trim_end_seconds | any | update_music: where playback stops within the track, in seconds |
| trim_start_seconds | any | update_music: where playback starts within the track, in seconds |
{
"name": "editor_edit",
"title": "Edit the video",
"description": "Polish the video in the editor; changes show in the next export.\n\nscene_note: edit one scene with a note (move, restyle, add or remove\nlayers and overlays, change the text of a lower third, title card or\ncallout, change motion); spends credits. Returns the changes and\nskipped_mutations: edits that didn't land (applied=false) or landed\ndifferently than asked (applied=true), each with a reason; check them.\nScene lengths follow the narration; the image, clip and voiceover layers\ncan't be removed. project_note: a note for the whole video, applied to\nup to 10 scenes per call; spends credits. captions: merge caption\nsettings. add_sfx: attach a sound effect to a segment. add_music /\nupdate_music: background music timed in seconds; a track's duration\nfollows from its trim.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"loop": {
"anyOf": [
{
"type": "boolean"
},
{
"type": "null"
}
],
"description": "Loop the music under the whole video"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The music track's name"
},
"action": {
"enum": [
"scene_note",
"project_note",
"captions",
"add_sfx",
"add_music",
"update_music"
],
"type": "string",
"description": "scene_note: segment_number, message; project_note: message; captions: caption_config; add_sfx: segment_number, library_track_id; add_music: library_track_id, optional name, volume, loop, start_seconds; update_music: track_id and any of name, volume, loop, start_seconds, trim_start_seconds, trim_end_seconds"
},
"volume": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Music volume 0-1; the 0.12 default sits under the narration, so raise it only if asked"
},
"message": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "The note in plain words, e.g. \"move the caption to the top\""
},
"track_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "update_music: a track id from editor_read action=music"
},
"project_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "Project id"
},
"start_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "Where the music starts in the video, in seconds"
},
"caption_config": {
"anyOf": [
{
"type": "object",
"additionalProperties": true
},
{
"type": "null"
}
],
"description": "captions: keys to merge into the caption settings (get_status shows them)"
},
"segment_number": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"description": "Segment number (1-based, from storyboard_read)"
},
"library_track_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"description": "A track id from editor_read action=audio_library"
},
"trim_end_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "update_music: where playback stops within the track, in seconds"
},
"trim_start_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"description": "update_music: where playback starts within the track, in seconds"
}
}
},
"annotations": {
"title": "Edit the video",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Render the finished video from the editor timeline; free. When the export job completes, get_status carries export_url.
| Parameter | Type | Description |
|---|---|---|
| project_id * | string | Project id |
{
"name": "export_video",
"title": "Export the video",
"description": "Render the finished video from the editor timeline; free. When the\nexport job completes, get_status carries export_url.",
"inputSchema": {
"type": "object",
"required": [
"project_id"
],
"properties": {
"project_id": {
"type": "string",
"description": "Project id"
}
}
},
"annotations": {
"title": "Export the video",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": true
}
}Framesail turns a brief into a finished video. Steps, in order: channel style -> script -> Analyze Script (finds the characters, environments, objects and voice blocks) -> reference images -> voices and voiceover -> storyboard (segments) -> segment images, some animated into clips -> export. Start and resume with get_status: the account and credits, each step's state and web link, running jobs, and the next step in plain words. A step called out of order is refused with that next step: do it instead of retrying. Generate tools return at once; call get_status with wait=true until the jobs finish. Work stays saved between sessions: never redo a step because you don't remember doing it. Spending: generate tools, render and notes spend credits, and so does a change to a real photo or B-roll that had no searches (a small AI step writes them); every other read, edit and export is free. Go one step at a time, show the user each result and its web link, and wait for a go-ahead unless they asked for the whole run. Before rendering, always call render with dry_run=true, show the estimate beside credits_available, and wait for a yes given after they saw it; an earlier "do it all" does not cover it. Never generate finished work again unless asked. model, settings and editable_sections (the prompt editor) apply to named items only and are saved to each for next time. Words: a segment is one storyboard item; a scene is one editor timeline item. A segment's image is generated first and can be animated into a clip; a talking head is a clip with lip sync. Real photos and B-roll are fetched, not generated. Overlays are on-screen text (lower thirds, title cards, callouts); an overlay segment is all on-screen text, full screen. The brief is what the video is about; the visual concept is how it looks. Each channel has exactly one channel style. The tools need a Pro, Studio or Scale plan; get_status explains. A 401 means the connection is no longer valid: ask the user to reconnect.
Names, descriptions and schemas were written by the server and are shown as data.