Tuney is an MCP server published by io.github.library-x, hosted at api.tuney.io. When last checked on 2026-11-21 it was working: it answers and lists its tools. It declares 15 tools, including list_styles, find_tracks, generate_track, get_task, wait_for_task.
Royalty-free music fitted to your length or video: find, generate and adjust tracks, score videos.
Nothing else in the archive shares these values.
List the genres, moods and tempos Tuney can find or generate music for. Call this before find_tracks or generate_track and pick the values that fit the user's brief.
No parameters.
{
"name": "list_styles",
"title": "List music styles",
"description": "List the genres, moods and tempos Tuney can find or generate music for.\n\n Call this before find_tracks or generate_track and pick the values that fit the user's brief.\n ",
"inputSchema": {
"type": "object",
"title": "list_stylesArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "list_stylesDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}None yet. Changes appear after a server's second daily check.
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.
Find ready-made Tuney tracks that match a brief. Previews are free. Best results: pass genre, mood and tempo values from list_styles (any one is enough). A free-text prompt works too, but it is matched on overall feel only, not on instruments, so check the genre, mood and tempo of what comes back. Each result has a cue_id and a preview URL. limit is 1 to 5; each result takes a few seconds. Pass the returned search_id to get more results for the same brief. Use adjust_track to change length or key, and download_track for the final file.
| Parameter | Type | Description |
|---|---|---|
| mood | any | |
| genre | any | |
| limit | integer | |
| tempo | any | |
| prompt | any | |
| search_id | any |
{
"name": "find_tracks",
"title": "Find ready-made tracks",
"description": "Find ready-made Tuney tracks that match a brief. Previews are free.\n\n Best results: pass genre, mood and tempo values from list_styles (any one is enough). A\n free-text prompt works too, but it is matched on overall feel only, not on instruments, so\n check the genre, mood and tempo of what comes back. Each result has a cue_id and a preview\n URL. limit is 1 to 5; each result takes a few seconds. Pass the returned search_id to get\n more results for the same brief. Use adjust_track to change length or key, and\n download_track for the final file.\n ",
"inputSchema": {
"type": "object",
"title": "find_tracksArguments",
"properties": {
"mood": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Mood",
"default": null
},
"genre": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Genre",
"default": null
},
"limit": {
"type": "integer",
"title": "Limit",
"default": 3
},
"tempo": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Tempo",
"default": null
},
"prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt",
"default": null
},
"search_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Search Id",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "find_tracksDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Compose a brand-new track from Tuney's hand-made musical elements, fitted to an exact length. Use genre, mood and tempo values from list_styles, or leave them empty for any style. Generation runs in the background: this returns a task_id, so call wait_for_task next. Previews are free.
| Parameter | Type | Description |
|---|---|---|
| mood | any | |
| build | string | one of ["none","ascending"] |
| genre | any | |
| tempo | any | |
| length_seconds | number |
{
"name": "generate_track",
"title": "Generate a new track",
"description": "Compose a brand-new track from Tuney's hand-made musical elements, fitted to an exact length.\n\n Use genre, mood and tempo values from list_styles, or leave them empty for any style.\n Generation runs in the background: this returns a task_id, so call wait_for_task next.\n Previews are free.\n ",
"inputSchema": {
"type": "object",
"title": "generate_trackArguments",
"properties": {
"mood": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Mood",
"default": null
},
"build": {
"enum": [
"none",
"ascending"
],
"type": "string",
"title": "Build",
"default": "none"
},
"genre": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Genre",
"default": null
},
"tempo": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Tempo",
"default": null
},
"length_seconds": {
"type": "number",
"title": "Length Seconds",
"default": 60
}
}
},
"outputSchema": {
"type": "object",
"title": "generate_trackDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Check a background task once: a generation, a download, or a video import, analysis, scoring or render. Prefer wait_for_task, which polls for you.
| Parameter | Type | Description |
|---|---|---|
| kind | string | one of ["generate","download","import_video","analyze_video","score_video","render_video"] |
| task_id * | string |
{
"name": "get_task",
"title": "Check a background task",
"description": "Check a background task once: a generation, a download, or a video import, analysis, scoring or render.\n\n Prefer wait_for_task, which polls for you.\n ",
"inputSchema": {
"type": "object",
"title": "get_taskArguments",
"required": [
"task_id"
],
"properties": {
"kind": {
"enum": [
"generate",
"download",
"import_video",
"analyze_video",
"score_video",
"render_video"
],
"type": "string",
"title": "Kind",
"default": "generate"
},
"task_id": {
"type": "string",
"title": "Task Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_taskDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Wait for a background task to finish, reporting progress along the way. kind is the one the starting tool returned: generate, download, import_video, analyze_video, score_video or render_video. Returns the finished track (with preview_url), the download_url, or the video result. If it is still running when the timeout passes, the result says so: call wait_for_task again with the same task_id and kind.
| Parameter | Type | Description |
|---|---|---|
| kind | string | one of ["generate","download","import_video","analyze_video","score_video","render_video"] |
| task_id * | string | |
| timeout_seconds | integer |
{
"name": "wait_for_task",
"title": "Wait for a background task",
"description": "Wait for a background task to finish, reporting progress along the way.\n\n kind is the one the starting tool returned: generate, download, import_video, analyze_video,\n score_video or render_video. Returns the finished track (with preview_url), the download_url,\n or the video result. If it is still running when the timeout passes, the result says so:\n call wait_for_task again with the same task_id and kind.\n ",
"inputSchema": {
"type": "object",
"title": "wait_for_taskArguments",
"required": [
"task_id"
],
"properties": {
"kind": {
"enum": [
"generate",
"download",
"import_video",
"analyze_video",
"score_video",
"render_video"
],
"type": "string",
"title": "Kind",
"default": "generate"
},
"task_id": {
"type": "string",
"title": "Task Id"
},
"timeout_seconds": {
"type": "integer",
"title": "Timeout Seconds",
"default": 50
}
}
},
"outputSchema": {
"type": "object",
"title": "wait_for_taskDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Get a track by cue_id: name, preview URL, length, bpm, key, style and sections.
| Parameter | Type | Description |
|---|---|---|
| cue_id * | string |
{
"name": "get_track",
"title": "Get a track",
"description": "Get a track by cue_id: name, preview URL, length, bpm, key, style and sections.",
"inputSchema": {
"type": "object",
"title": "get_trackArguments",
"required": [
"cue_id"
],
"properties": {
"cue_id": {
"type": "string",
"title": "Cue Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_trackDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Re-render a track with changes, keeping it musically coherent. - length_seconds: fit the track to an exact duration (the engine recomposes the arrangement). - turning_point_seconds: add a turning point at that second, where the music changes character (new arrangement after the point, an audible transition). Combine with length_seconds to lengthen a track and place the turning point in one go. If the track already has a turning point, this moves it. - ending: how the track ends, "fade_out" or "short" (a stab on the last beat). The track keeps its length (or the length_seconds you give) within a quarter of a second either way. - time_stretch: tempo factor, for example 0.9 slower or 1.1 faster. - pitch_shift: semitones, for example -2 or 3. - mute / unmute: stems by name: melody, chords, bass, drums. - regenerate: stems to re-pick musical material for (melody, chords, bass, drums); all four give a fresh take on the same brief. Runs in the background: returns a task_id for wait_for_task.
| Parameter | Type | Description |
|---|---|---|
| mute | any | |
| cue_id * | string | |
| ending | any | |
| unmute | any | |
| regenerate | any | |
| pitch_shift | any | |
| time_stretch | any | |
| length_seconds | any | |
| turning_point_seconds | any |
{
"name": "adjust_track",
"title": "Adjust a track",
"description": "Re-render a track with changes, keeping it musically coherent.\n\n - length_seconds: fit the track to an exact duration (the engine recomposes the arrangement).\n - turning_point_seconds: add a turning point at that second, where the music changes character\n (new arrangement after the point, an audible transition). Combine with length_seconds to\n lengthen a track and place the turning point in one go. If the track already has a turning\n point, this moves it.\n - ending: how the track ends, \"fade_out\" or \"short\" (a stab on the last beat). The track keeps\n its length (or the length_seconds you give) within a quarter of a second either way.\n - time_stretch: tempo factor, for example 0.9 slower or 1.1 faster.\n - pitch_shift: semitones, for example -2 or 3.\n - mute / unmute: stems by name: melody, chords, bass, drums.\n - regenerate: stems to re-pick musical material for (melody, chords, bass, drums); all four\n give a fresh take on the same brief.\n Runs in the background: returns a task_id for wait_for_task.\n ",
"inputSchema": {
"type": "object",
"title": "adjust_trackArguments",
"required": [
"cue_id"
],
"properties": {
"mute": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Mute",
"default": null
},
"cue_id": {
"type": "string",
"title": "Cue Id"
},
"ending": {
"anyOf": [
{
"enum": [
"fade_out",
"short"
],
"type": "string"
},
{
"type": "null"
}
],
"title": "Ending",
"default": null
},
"unmute": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Unmute",
"default": null
},
"regenerate": {
"anyOf": [
{
"type": "array",
"items": {
"type": "string"
}
},
{
"type": "null"
}
],
"title": "Regenerate",
"default": null
},
"pitch_shift": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Pitch Shift",
"default": null
},
"time_stretch": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Time Stretch",
"default": null
},
"length_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Length Seconds",
"default": null
},
"turning_point_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Turning Point Seconds",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "adjust_trackDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Get a download link for the final file: mp3, wav, or a zip of stems. Signed in, this spends Tuney credits and the file is clean. Without sign-in it is free and the file has the pulsing tone over it (the result says listen_only). Returns download_url right away when the file is cached, otherwise a task_id to pass to wait_for_task with kind="download". Links expire, so share them promptly. download_url is on the Tuney API host; download_direct_url is the same file in Cloud Storage. For format="stems" the link is a zip with one mp3 per part; the result's `contents` map gives the readable name of each file (melody, chords, bass, drums, swoosh fx, impact fx). To show stems to the user: fetch the zip, unzip it, rename the files with that map and attach them. Never download the same track twice.
| Parameter | Type | Description |
|---|---|---|
| cue_id * | string | |
| format | string | one of ["mp3","wav","stems"] |
{
"name": "download_track",
"title": "Download a track",
"description": "Get a download link for the final file: mp3, wav, or a zip of stems.\n\n Signed in, this spends Tuney credits and the file is clean. Without sign-in it is free and\n the file has the pulsing tone over it (the result says listen_only).\n Returns download_url right away when the file is cached, otherwise a task_id to pass to\n wait_for_task with kind=\"download\". Links expire, so share them promptly. download_url is on\n the Tuney API host; download_direct_url is the same file in Cloud Storage.\n For format=\"stems\" the link is a zip with one mp3 per part; the result's `contents` map\n gives the readable name of each file (melody, chords, bass, drums, swoosh fx, impact fx).\n To show stems to the user: fetch the zip, unzip it, rename the files with that map and\n attach them. Never download the same track twice.\n ",
"inputSchema": {
"type": "object",
"title": "download_trackArguments",
"required": [
"cue_id"
],
"properties": {
"cue_id": {
"type": "string",
"title": "Cue Id"
},
"format": {
"enum": [
"mp3",
"wav",
"stems"
],
"type": "string",
"title": "Format",
"default": "mp3"
}
}
},
"outputSchema": {
"type": "object",
"title": "download_trackDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Show whether the user is signed in to Tuney, which account it is, and its credit balance with a link to buy more.
No parameters.
{
"name": "get_account",
"title": "Show the signed-in account",
"description": "Show whether the user is signed in to Tuney, which account it is, and its credit balance with a link to buy more.",
"inputSchema": {
"type": "object",
"title": "get_accountArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "get_accountDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Start signing in to Tuney. Signed in, audio is clean (no pulsing tone) and the user has their own library and credits. Call it only when the user asks to sign in or wants clean files; everything works without it. Without a sign-in, this call makes the app show its Tuney sign-in (in Claude Code the user picks Authenticate for Tuney under /mcp), where an account is free to create. Tell the user first: some apps pause the Tuney tools until the sign-in is finished. When already signed in, it says so. Then call get_track with the cue_id of each track made before the sign-in: it comes back clean, under a new cue_id in the user's library. Render a video again to get clean music under it.
No parameters.
{
"name": "sign_in",
"title": "Sign in to Tuney",
"description": "Start signing in to Tuney. Signed in, audio is clean (no pulsing tone) and the user has their own library and credits.\n\n Call it only when the user asks to sign in or wants clean files; everything works without it.\n Without a sign-in, this call makes the app show its Tuney sign-in (in Claude Code the user\n picks Authenticate for Tuney under /mcp), where an account is free to create. Tell the user\n first: some apps pause the Tuney tools until the sign-in is finished.\n When already signed in, it says so. Then call get_track with the cue_id of each track made\n before the sign-in: it comes back clean, under a new cue_id in the user's library. Render a\n video again to get clean music under it.\n ",
"inputSchema": {
"type": "object",
"title": "sign_inArguments",
"properties": {}
},
"outputSchema": {
"type": "object",
"title": "sign_inDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Create a one-time link for sending a video file (MP4, MOV or M4V) to Tuney for scoring. Use this when the video is a local file, for example one the user attached or one in the working directory. Send the file with the curl command in `example` (HTTP PUT of the raw file); the response contains the video_id to pass to score_video. If the video is already online, use import_video with its link instead.
| Parameter | Type | Description |
|---|---|---|
| filename | string |
{
"name": "get_video_upload_link",
"title": "Get a link to upload a video",
"description": "Create a one-time link for sending a video file (MP4, MOV or M4V) to Tuney for scoring.\n\n Use this when the video is a local file, for example one the user attached or one in the\n working directory. Send the file with the curl command in `example` (HTTP PUT of the raw\n file); the response contains the video_id to pass to score_video. If the video is already\n online, use import_video with its link instead.\n ",
"inputSchema": {
"type": "object",
"title": "get_video_upload_linkArguments",
"properties": {
"filename": {
"type": "string",
"title": "Filename",
"default": "video.mp4"
}
}
},
"outputSchema": {
"type": "object",
"title": "get_video_upload_linkDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Bring a video into Tuney from a public https link that returns the file itself (not a web page). Returns the video_id to pass to score_video, analyze_video or render_video. Videos up to 200 MB and 10 minutes. For a local file, use get_video_upload_link instead.
| Parameter | Type | Description |
|---|---|---|
| url * | string |
{
"name": "import_video",
"title": "Import a video from a link",
"description": "Bring a video into Tuney from a public https link that returns the file itself (not a web page).\n\n Returns the video_id to pass to score_video, analyze_video or render_video. Videos up to\n 200 MB and 10 minutes. For a local file, use get_video_upload_link instead.\n ",
"inputSchema": {
"type": "object",
"title": "import_videoArguments",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "Url"
}
}
},
"outputSchema": {
"type": "object",
"title": "import_videoDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Show what Tuney sees in a video: picture cuts with their strength, where people speak, and a sonic-logo guess. Optional: score_video analyses the video by itself. Use this to discuss the edit with the user first, for example to pick the turning point or the moment the music should end.
| Parameter | Type | Description |
|---|---|---|
| video_id * | string |
{
"name": "analyze_video",
"title": "Analyze a video",
"description": "Show what Tuney sees in a video: picture cuts with their strength, where people speak, and a sonic-logo guess.\n\n Optional: score_video analyses the video by itself. Use this to discuss the edit with the user\n first, for example to pick the turning point or the moment the music should end.\n ",
"inputSchema": {
"type": "object",
"title": "analyze_videoArguments",
"required": [
"video_id"
],
"properties": {
"video_id": {
"type": "string",
"title": "Video Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "analyze_videoDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": true,
"idempotentHint": true,
"destructiveHint": false
}
}Compose music to a video and, by default, return the video with the music under it. Tuney finds the picture cuts, speech and sonic logo, then arranges a track to them: the music ends where the logo starts (or at the end), the turning point lands on the strongest cut in the middle, hits land on other strong cuts outside speech, and the music is lowered while people speak in the rendered video. - prompt: describe the music ("upbeat pop for a sneaker ad"); or cue_id: one of the user's tracks. - ending: "fade" lands exactly on the length; "short" ends on a stab. - turning_point_seconds / no_turning_point: override the automatic turning point. - music_end_seconds / logo_start_seconds: where the music must stop (a sonic logo starts). - hits: sound effects on strong cuts; render: also return the scored video. Scoring takes about a minute; if the result says timed_out, call wait_for_task with the task_id and kind="score_video". The result has the track (preview_url), the plan, and the video link when rendered. Previews and renders are free; downloading the track costs credits.
| Parameter | Type | Description |
|---|---|---|
| hits | boolean | |
| cue_id | any | |
| ending | string | one of ["fade","short"] |
| prompt | any | |
| render | boolean | |
| video_id * | string | |
| no_turning_point | boolean | |
| music_end_seconds | any | |
| logo_start_seconds | any | |
| turning_point_seconds | any |
{
"name": "score_video",
"title": "Score a video",
"description": "Compose music to a video and, by default, return the video with the music under it.\n\n Tuney finds the picture cuts, speech and sonic logo, then arranges a track to them: the music\n ends where the logo starts (or at the end), the turning point lands on the strongest cut in\n the middle, hits land on other strong cuts outside speech, and the music is lowered while\n people speak in the rendered video.\n\n - prompt: describe the music (\"upbeat pop for a sneaker ad\"); or cue_id: one of the user's tracks.\n - ending: \"fade\" lands exactly on the length; \"short\" ends on a stab.\n - turning_point_seconds / no_turning_point: override the automatic turning point.\n - music_end_seconds / logo_start_seconds: where the music must stop (a sonic logo starts).\n - hits: sound effects on strong cuts; render: also return the scored video.\n\n Scoring takes about a minute; if the result says timed_out, call wait_for_task with the\n task_id and kind=\"score_video\". The result has the track (preview_url), the plan, and the\n video link when rendered. Previews and renders are free; downloading the track costs credits.\n ",
"inputSchema": {
"type": "object",
"title": "score_videoArguments",
"required": [
"video_id"
],
"properties": {
"hits": {
"type": "boolean",
"title": "Hits",
"default": true
},
"cue_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cue Id",
"default": null
},
"ending": {
"enum": [
"fade",
"short"
],
"type": "string",
"title": "Ending",
"default": "fade"
},
"prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Prompt",
"default": null
},
"render": {
"type": "boolean",
"title": "Render",
"default": true
},
"video_id": {
"type": "string",
"title": "Video Id"
},
"no_turning_point": {
"type": "boolean",
"title": "No Turning Point",
"default": false
},
"music_end_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Music End Seconds",
"default": null
},
"logo_start_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Logo Start Seconds",
"default": null
},
"turning_point_seconds": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"title": "Turning Point Seconds",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "score_videoDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Put one of the user's tracks under a video, for example after adjust_track changed the scored track. duck lowers the music while people speak. music_volume and video_volume are gains from 0 to 2 (1 leaves the level unchanged). Returns a link to the rendered MP4.
| Parameter | Type | Description |
|---|---|---|
| duck | boolean | |
| cue_id * | string | |
| video_id * | string | |
| music_volume | number | |
| video_volume | number |
{
"name": "render_video",
"title": "Render a video with a track",
"description": "Put one of the user's tracks under a video, for example after adjust_track changed the scored track.\n\n duck lowers the music while people speak. music_volume and video_volume are gains from 0 to 2\n (1 leaves the level unchanged). Returns a link to the rendered MP4.\n ",
"inputSchema": {
"type": "object",
"title": "render_videoArguments",
"required": [
"video_id",
"cue_id"
],
"properties": {
"duck": {
"type": "boolean",
"title": "Duck",
"default": true
},
"cue_id": {
"type": "string",
"title": "Cue Id"
},
"video_id": {
"type": "string",
"title": "Video Id"
},
"music_volume": {
"type": "number",
"title": "Music Volume",
"default": 1
},
"video_volume": {
"type": "number",
"title": "Video Volume",
"default": 1
}
}
},
"outputSchema": {
"type": "object",
"title": "render_videoDictOutput",
"additionalProperties": true
},
"annotations": {
"readOnlyHint": false,
"openWorldHint": true,
"idempotentHint": false,
"destructiveHint": false
}
}Tuney composes royalty-free music from hand-made, modular musical elements and fits it to an exact length. Typical flow: list_styles -> find_tracks with a genre, mood and tempo from that list (previews are free; offer the user two or three) or generate_track -> wait_for_task -> adjust_track if the length, tempo, key or stems need changing -> download_track. Preview and download links are signed and expire, so give them to the user promptly. If a tool reports missing credits, send the user to the purchase link it returns instead of retrying. Presenting a track: give its name, length, bpm, key and the preview link, then offer stems and adjustments. In a client that can open web pages (for example the Claude desktop app's browser pane), open the preview URL there so the user can listen right away. When the user wants stems, call download_track with format "stems", fetch the zip, unzip it, rename the files with the `contents` map in the result (melody, chords, bass, drums, swoosh fx, impact fx) and attach them to the conversation. Never download the same track twice. Scoring a video: get it in with import_video (a public link to the file) or get_video_upload_link (a local file, sent with curl), then call score_video with a prompt or one of the user's tracks. It composes to the picture cuts, ends before a sonic logo, and returns the track, the plan (turning point, hits, ending) and the rendered video. Tell the user where the turning point and hits landed. After adjust_track on that track, call render_video to put the new version under the video. File links (preview_url, download_url, video.url) are on the Tuney API host; the *_direct_url fields point at Cloud Storage. Fetch the API-host link first; if a sandbox blocks both, tell the user to allow the API host in their network settings, and give them the links to open. No sign-in is needed: every tool works without one. Results then say listen_only, because all audio has a pulsing tone over it (previews, downloads and the music in rendered videos), and downloads are free. Tell the user once. Signed in, audio is clean and downloads spend the user's Tuney credits. Call sign_in only when the user asks to sign in or wants clean files. After sign-in, call get_track with the cue_id of each track made before it: it comes back clean under a new cue_id (the result says copied_from), and render a video again to get clean music under it.
Names, descriptions and schemas were written by the server and are shown as data.