TTSForFree is an MCP server published by io.github.CalmNguyen, hosted at api.ttsforfree.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 28 tools, including list_languages, list_voices, get_voice_details, list_my_custom_voices, list_favorite_voices.
Generate AI voices, text-to-speech, subtitles, transcription, and video localization.
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.
List every language supported by TTSForFree text-to-speech. Returns language codes to pass to list_voices.
No parameters.
{
"name": "list_languages",
"title": "List languages",
"description": "List every language supported by TTSForFree text-to-speech. Returns language codes to pass to list_voices.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "List languages",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Search the AI voice catalog for one language. Each result has a `voice` token (v1:...) - pass it unchanged as `voice` to text_to_speech, multi_voice_to_speech or srt_to_speech. Results are sorted by popularity; `can_use=false` means the user's plan cannot use that voice. Prefer the user's favorite or custom voices when they exist.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| query | string | Optional keywords matched against name, style, persona and use case, e.g. 'warm narrator', 'news', 'young'. |
| gender | string | one of ["male","female"] |
| language * | string | Language code from list_languages, e.g. en, vi, es, ja. |
| provider | string | Optional voice engine filter. Gemini/OpenAI voices are the most expressive. |
| only_usable | boolean | Hide voices the current plan cannot use. |
{
"name": "list_voices",
"title": "Find voices",
"description": "Search the AI voice catalog for one language. Each result has a `voice` token (v1:...) - pass it unchanged as `voice` to text_to_speech, multi_voice_to_speech or srt_to_speech. Results are sorted by popularity; `can_use=false` means the user's plan cannot use that voice. Prefer the user's favorite or custom voices when they exist.",
"inputSchema": {
"type": "object",
"required": [
"language"
],
"properties": {
"limit": {
"type": "integer",
"default": 25,
"maximum": 100,
"minimum": 1
},
"query": {
"type": "string",
"description": "Optional keywords matched against name, style, persona and use case, e.g. 'warm narrator', 'news', 'young'."
},
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"language": {
"type": "string",
"description": "Language code from list_languages, e.g. en, vi, es, ja."
},
"provider": {
"enum": [
"Google",
"Azure",
"Gemini",
"OpenAI",
"FPT"
],
"type": "string",
"description": "Optional voice engine filter. Gemini/OpenAI voices are the most expressive."
},
"only_usable": {
"type": "boolean",
"default": true,
"description": "Hide voices the current plan cannot use."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Find voices",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get full metadata for one voice token: persona, use case, accent, pitch, styles, preview audio and credit cost.
| Parameter | Type | Description |
|---|---|---|
| voice * | string | Voice token (v1:...) from list_voices, favorites or custom voices. |
{
"name": "get_voice_details",
"title": "Voice details",
"description": "Get full metadata for one voice token: persona, use case, accent, pitch, styles, preview audio and credit cost.",
"inputSchema": {
"type": "object",
"required": [
"voice"
],
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_voices, favorites or custom voices."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Voice details",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the user's personal voices created with Voice Design (from a text prompt) or Voice Clone (from an audio sample), plus the remaining custom-voice quota. Use `voice` from the result in any speech tool.
No parameters.
{
"name": "list_my_custom_voices",
"title": "My custom voices",
"description": "List the user's personal voices created with Voice Design (from a text prompt) or Voice Clone (from an audio sample), plus the remaining custom-voice quota. Use `voice` from the result in any speech tool.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "My custom voices",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the voices the user marked as favorites, in their saved order. Check this first when the user did not name a voice.
No parameters.
{
"name": "list_favorite_voices",
"title": "My favorite voices",
"description": "List the voices the user marked as favorites, in their saved order. Check this first when the user did not name a voice.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "My favorite voices",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Save a voice to the user's favorites (only when the user asks).
| Parameter | Type | Description |
|---|---|---|
| voice * | string | Voice token (v1:...) from list_voices. |
{
"name": "add_favorite_voice",
"title": "Add favorite voice",
"description": "Save a voice to the user's favorites (only when the user asks).",
"inputSchema": {
"type": "object",
"required": [
"voice"
],
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_voices."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Add favorite voice",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Remove a voice from the user's favorites (only when the user asks).
| Parameter | Type | Description |
|---|---|---|
| voice * | string | Voice token (v1:...) from list_favorite_voices. |
{
"name": "remove_favorite_voice",
"title": "Remove favorite voice",
"description": "Remove a voice from the user's favorites (only when the user asks).",
"inputSchema": {
"type": "object",
"required": [
"voice"
],
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_favorite_voices."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Remove favorite voice",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}Create a new personal AI voice from a natural-language description (Gemini Voice Design). Uses one slot of the user's custom-voice quota - confirm with the user first. Good for a unique narrator or a character voice in a video/podcast. Returns the new `voice` token.
| Parameter | Type | Description |
|---|---|---|
| gender * | string | one of ["male","female"] |
| prompt * | string | Describe age, accent, timbre, personality, energy and pace. Example: 'Calm male documentary narrator in his 40s, deep warm timbre, slow confident pace, neutral American accent.' |
| display_name * | string | |
| language_code * | string | BCP-47 locale, e.g. en-US, vi-VN. |
{
"name": "design_custom_voice",
"title": "Design a custom voice",
"description": "Create a new personal AI voice from a natural-language description (Gemini Voice Design). Uses one slot of the user's custom-voice quota - confirm with the user first. Good for a unique narrator or a character voice in a video/podcast. Returns the new `voice` token.",
"inputSchema": {
"type": "object",
"required": [
"display_name",
"gender",
"language_code",
"prompt"
],
"properties": {
"gender": {
"enum": [
"male",
"female"
],
"type": "string"
},
"prompt": {
"type": "string",
"maxLength": 1500,
"minLength": 20,
"description": "Describe age, accent, timbre, personality, energy and pace. Example: 'Calm male documentary narrator in his 40s, deep warm timbre, slow confident pace, neutral American accent.'"
},
"display_name": {
"type": "string",
"maxLength": 60,
"minLength": 1
},
"language_code": {
"type": "string",
"description": "BCP-47 locale, e.g. en-US, vi-VN."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Design a custom voice",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Show the user's plan tier, remaining characters/credits, max characters per request, max blocks per multi-voice/SRT job and API rate limits. Call before large jobs.
No parameters.
{
"name": "get_account_status",
"title": "Account status",
"description": "Show the user's plan tier, remaining characters/credits, max characters per request, max blocks per multi-voice/SRT job and API rate limits. Call before large jobs.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Account status",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Convert one text into one MP3 with one voice. Use for narration, voiceover scripts, articles, lessons, announcements or any audio whose length can follow the speech. Consumes credits (characters x voice rate). Returns job_id, status and audio_url when ready.
| Parameter | Type | Description |
|---|---|---|
| text * | string | Text to read. Plain text; long text is split and merged automatically. |
| pitch | number | Only some providers support pitch. |
| voice * | string | Voice token (v1:...). |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
{
"name": "text_to_speech",
"title": "Text to speech",
"description": "Convert one text into one MP3 with one voice. Use for narration, voiceover scripts, articles, lessons, announcements or any audio whose length can follow the speech. Consumes credits (characters x voice rate). Returns job_id, status and audio_url when ready.",
"inputSchema": {
"type": "object",
"required": [
"text",
"voice"
],
"properties": {
"text": {
"type": "string",
"minLength": 1,
"description": "Text to read. Plain text; long text is split and merged automatically."
},
"pitch": {
"type": "number",
"default": 0,
"maximum": 100,
"minimum": -100,
"description": "Only some providers support pitch."
},
"voice": {
"type": "string",
"description": "Voice token (v1:...)."
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Text to speech",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Render ordered segments, each with its own voice, into ONE merged MP3. Use for podcasts, dialogues, interviews, audio dramas or explainer videos with several speakers when there are no fixed timestamps. Consumes credits.
| Parameter | Type | Description |
|---|---|---|
| segments * | array | |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
{
"name": "multi_voice_to_speech",
"title": "Multi-voice audio (podcast / dialogue)",
"description": "Render ordered segments, each with its own voice, into ONE merged MP3. Use for podcasts, dialogues, interviews, audio dramas or explainer videos with several speakers when there are no fixed timestamps. Consumes credits.",
"inputSchema": {
"type": "object",
"required": [
"segments"
],
"properties": {
"segments": {
"type": "array",
"items": {
"type": "object",
"required": [
"text",
"voice"
],
"properties": {
"text": {
"type": "string",
"minLength": 1
},
"speed": {
"type": "number",
"default": 1,
"maximum": 2.5,
"minimum": 0.5
},
"voice": {
"type": "string",
"description": "Voice token (v1:...)."
},
"volume": {
"type": "number",
"default": 1,
"maximum": 2,
"minimum": 0
},
"pause_after_ms": {
"type": "integer",
"default": 300,
"maximum": 10000,
"minimum": 0,
"description": "Silence after this segment."
}
},
"additionalProperties": false
},
"minItems": 1
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Multi-voice audio (podcast / dialogue)",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Create ONE MP3 that follows a subtitle timeline: every cue starts at its timestamp and speech speed auto-fits the cue duration. Use for video voiceover, dubbing translated subtitles, YouTube localization, tutorials and any edit where audio must line up with existing video. Pass either raw `srt` (SRT or WebVTT text) or `segments` with start_ms/end_ms. For several speakers set `speaker_voices` and prefix cue text with '[Name]' or 'Name:'. The resulting MP3 starts at 00:00 of the video, so it can be muxed directly with ffmpeg (commands are returned). Consumes credits.
| Parameter | Type | Description |
|---|---|---|
| srt | string | Full SRT or WebVTT content. |
| voice | string | Default voice token for cues without a speaker/voice. |
| segments | array | Alternative to srt: timed segments. |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
| speaker_voices | object | Map speaker name -> voice token, e.g. {"Host": "v1:...", "Guest": "v1:..."}. |
| max_speech_rate | number | Highest auto-fit speed when a cue is too short for its text. |
| min_speech_rate | number | Lowest auto-fit speed. Set min = max for a fixed speed. |
Check a speech job created earlier. Returns status (PENDING | SUCCESS | ERROR) and audio_url once SUCCESS. Never guess or fetch an audio URL before SUCCESS.
| Parameter | Type | Description |
|---|---|---|
| job_id * | integer | |
| job_type * | string | single = text_to_speech, multi = multi_voice_to_speech, srt = srt_to_speech. |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
{
"name": "get_job_status",
"title": "Job status",
"description": "Check a speech job created earlier. Returns status (PENDING | SUCCESS | ERROR) and audio_url once SUCCESS. Never guess or fetch an audio URL before SUCCESS.",
"inputSchema": {
"type": "object",
"required": [
"job_id",
"job_type"
],
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
},
"job_type": {
"enum": [
"single",
"multi",
"srt"
],
"type": "string",
"description": "single = text_to_speech, multi = multi_voice_to_speech, srt = srt_to_speech."
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Job status",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}List the user's most recent speech jobs with status and audio URLs, to reuse earlier audio instead of paying again.
| Parameter | Type | Description |
|---|---|---|
| limit | integer | |
| job_type | string | one of ["single","multi","srt"] |
{
"name": "list_recent_jobs",
"title": "Recent jobs",
"description": "List the user's most recent speech jobs with status and audio URLs, to reuse earlier audio instead of paying again.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1
},
"job_type": {
"enum": [
"single",
"multi",
"srt"
],
"type": "string",
"default": "single"
}
},
"additionalProperties": false
},
"annotations": {
"title": "Recent jobs",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get a multi_voice_to_speech or srt_to_speech job with every segment: text, voice and its own audio_url, plus the merged audio. Use it to build captions or a Remotion/NLE timeline (one <Sequence> per segment; measure each file's duration in the renderer).
| Parameter | Type | Description |
|---|---|---|
| job_id * | integer |
{
"name": "get_job_detail",
"title": "Job segments (for Remotion / editors)",
"description": "Get a multi_voice_to_speech or srt_to_speech job with every segment: text, voice and its own audio_url, plus the merged audio. Use it to build captions or a Remotion/NLE timeline (one <Sequence> per segment; measure each file's duration in the renderer).",
"inputSchema": {
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Job segments (for Remotion / editors)",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Get a one-time URL to upload a local video or audio file (mp4, mov, webm, mkv, mp3, wav, m4a...) up to 2 GB. Upload with HTTP PUT of the raw bytes, e.g. `curl -T video.mp4 "<upload_url>"` (valid 15 minutes), then pass `public_url` to transcribe_media or localize_video. Only files uploaded here (or on ttsforfree.com) are accepted; YouTube and other external links are never downloaded. If you cannot run commands, ask the user to upload the file on https://ttsforfree.com/en/video-localization/ and paste the file link.
| Parameter | Type | Description |
|---|---|---|
| file_name * | string | Original file name with extension, e.g. lesson-01.mp4 |
| file_size_bytes | integer |
{
"name": "create_upload_url",
"title": "Upload a video/audio file",
"description": "Get a one-time URL to upload a local video or audio file (mp4, mov, webm, mkv, mp3, wav, m4a...) up to 2 GB. Upload with HTTP PUT of the raw bytes, e.g. `curl -T video.mp4 \"<upload_url>\"` (valid 15 minutes), then pass `public_url` to transcribe_media or localize_video. Only files uploaded here (or on ttsforfree.com) are accepted; YouTube and other external links are never downloaded. If you cannot run commands, ask the user to upload the file on https://ttsforfree.com/en/video-localization/ and paste the file link.",
"inputSchema": {
"type": "object",
"required": [
"file_name"
],
"properties": {
"file_name": {
"type": "string",
"description": "Original file name with extension, e.g. lesson-01.mp4"
},
"file_size_bytes": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Upload a video/audio file",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Speech-to-text for an uploaded video or audio file: returns timestamped SRT (the timeline to rewrite, translate or re-voice with srt_to_speech). Credits are charged per second of media, measured by the server. Use language = the spoken language code from list_languages.
| Parameter | Type | Description |
|---|---|---|
| language * | string | Spoken language code, e.g. vi, en, ja. |
| media_url * | string | public_url from create_upload_url (or a ttsforfree CDN link). |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
| multi_speaker | boolean | Several people talk (drama, interview, podcast): the whole file is sent at once for speaker detection, and each SRT cue starts with [Speaker N] (same N = same person across the whole file). |
{
"name": "transcribe_media",
"title": "Transcribe video/audio to SRT",
"description": "Speech-to-text for an uploaded video or audio file: returns timestamped SRT (the timeline to rewrite, translate or re-voice with srt_to_speech). Credits are charged per second of media, measured by the server. Use language = the spoken language code from list_languages.",
"inputSchema": {
"type": "object",
"required": [
"media_url",
"language"
],
"properties": {
"language": {
"type": "string",
"description": "Spoken language code, e.g. vi, en, ja."
},
"media_url": {
"type": "string",
"description": "public_url from create_upload_url (or a ttsforfree CDN link)."
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
},
"multi_speaker": {
"type": "boolean",
"default": false,
"description": "Several people talk (drama, interview, podcast): the whole file is sent at once for speaker detection, and each SRT cue starts with [Speaker N] (same N = same person across the whole file)."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Transcribe video/audio to SRT",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Check a transcribe_media job and get its SRT once finished.
| Parameter | Type | Description |
|---|---|---|
| job_id * | integer | |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
{
"name": "get_transcription",
"title": "Transcription status",
"description": "Check a transcribe_media job and get its SRT once finished.",
"inputSchema": {
"type": "object",
"required": [
"job_id"
],
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Transcription status",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Estimate the credits to dub one video into one or more languages (speech-to-text + translation + voice + video merge) before running localize_video. Pass video_url (duration is measured) or duration_seconds.
| Parameter | Type | Description |
|---|---|---|
| targets * | array | One entry per target language (the server allows 10 per job by default). |
| video_url | string | |
| source_language * | string | |
| duration_seconds | number |
{
"name": "estimate_video_localization",
"title": "Estimate video dubbing cost",
"description": "Estimate the credits to dub one video into one or more languages (speech-to-text + translation + voice + video merge) before running localize_video. Pass video_url (duration is measured) or duration_seconds.",
"inputSchema": {
"type": "object",
"required": [
"source_language",
"targets"
],
"properties": {
"targets": {
"type": "array",
"items": {
"type": "object",
"required": [
"language",
"voice"
],
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) for that language from list_voices / favorites / custom voices. With multi_speaker it is the default voice for speakers without their own."
},
"language": {
"type": "string",
"description": "Target language code, e.g. en, es, ja."
},
"speaker_voices": {
"type": "object",
"description": "multi_speaker only: voice per speaker for this language, e.g. {\"0\": \"v1:...\", \"1\": \"v1:...\"}.",
"additionalProperties": {
"type": "string"
}
}
},
"additionalProperties": false
},
"maxItems": 20,
"minItems": 1,
"description": "One entry per target language (the server allows 10 per job by default)."
},
"video_url": {
"type": "string"
},
"source_language": {
"type": "string"
},
"duration_seconds": {
"type": "number",
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Estimate video dubbing cost",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Full automatic dubbing of an uploaded video: transcribe once, translate, voice every target language with its own voice and render a dubbed video per language. Each language returns an audio_url (voice track aligned to the original timeline - upload it to YouTube Studio as a multi-language audio track) and a final_video_url. Takes several minutes: returns job_guids immediately; poll get_localization_status. Confirm the cost with estimate_video_localization for long videos. Several characters (drama, film, interview)? Set multi_speaker = true: speakers are detected on the whole video and each one can get its own voice - pass speaker_voices per target if you already know them, otherwise the job pauses with current_step WaitingSpeakerVoices and get_localization_status lists the speakers with sample lines; ask the user which voice fits each character, then call set_speaker_voices.
| Parameter | Type | Description |
|---|---|---|
| targets * | array | One entry per target language (the server allows 10 per job by default). |
| video_url * | string | public_url from create_upload_url. |
| multi_speaker | boolean | Dub each character with its own voice. Speakers are detected on the whole video (labels 0, 1, 2... in order of appearance). |
| source_language * | string | Spoken language of the video, e.g. vi. |
| speaker_voice_step | string | multi_speaker without speaker_voices: pause for voice choice after transcription (srt) or after translation (translated, shows translated sample lines). |
| original_audio_volume_percent | integer |
Status of localize_video jobs: current step, and when Completed the dubbed audio_url, final_video_url and translated SRT for each language. multi_speaker jobs waiting for voices have waiting_speaker_voices = true and a `speakers` list (lines, seconds, sample and translated sample lines) - then call set_speaker_voices.
| Parameter | Type | Description |
|---|---|---|
| job_guids * | array | |
| wait_seconds | integer | Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id. |
{
"name": "get_localization_status",
"title": "Video dubbing status",
"description": "Status of localize_video jobs: current step, and when Completed the dubbed audio_url, final_video_url and translated SRT for each language. multi_speaker jobs waiting for voices have waiting_speaker_voices = true and a `speakers` list (lines, seconds, sample and translated sample lines) - then call set_speaker_voices.",
"inputSchema": {
"type": "object",
"required": [
"job_guids"
],
"properties": {
"job_guids": {
"type": "array",
"items": {
"type": "string"
},
"maxItems": 20,
"minItems": 1
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Video dubbing status",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}For a multi_speaker localize_video job waiting at WaitingSpeakerVoices: give each speaker (key = speaker label from get_localization_status, e.g. "0") a voice token for that job's language, then dubbing continues. Speakers you leave out use the job's main voice. Pick voices that fit each character (gender, age, tone from the sample lines) and confirm with the user. translate_first = true continues to translation and pauses again with translated sample lines. Can also be called earlier, while the job is still transcribing or translating.
| Parameter | Type | Description |
|---|---|---|
| job_guid * | string | job_guid of one language from localize_video. |
| speaker_voices | object | {"0": "v1:...", "1": "v1:..."} |
| translate_first | boolean | Translate first and choose voices after (pauses again). |
{
"name": "set_speaker_voices",
"title": "Choose a voice per character",
"description": "For a multi_speaker localize_video job waiting at WaitingSpeakerVoices: give each speaker (key = speaker label from get_localization_status, e.g. \"0\") a voice token for that job's language, then dubbing continues. Speakers you leave out use the job's main voice. Pick voices that fit each character (gender, age, tone from the sample lines) and confirm with the user. translate_first = true continues to translation and pauses again with translated sample lines. Can also be called earlier, while the job is still transcribing or translating.",
"inputSchema": {
"type": "object",
"required": [
"job_guid"
],
"properties": {
"job_guid": {
"type": "string",
"description": "job_guid of one language from localize_video."
},
"speaker_voices": {
"type": "object",
"description": "{\"0\": \"v1:...\", \"1\": \"v1:...\"}",
"additionalProperties": {
"type": "string"
}
},
"translate_first": {
"type": "boolean",
"default": false,
"description": "Translate first and choose voices after (pauses again)."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Choose a voice per character",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}For a multi_speaker localize_video job: every source subtitle line with block_id, time, detected speaker and (after translation) the translated line. Use it when speaker detection looks wrong (fewer speakers than characters, a child merged with an adult, a line given to the wrong person): read the lines, work out who says each one from the story, then fix them with set_speaker_lines before set_speaker_voices.
| Parameter | Type | Description |
|---|---|---|
| job_guid * | string | job_guid of one language from localize_video. |
{
"name": "get_speaker_lines",
"title": "List subtitle lines with their speaker",
"description": "For a multi_speaker localize_video job: every source subtitle line with block_id, time, detected speaker and (after translation) the translated line. Use it when speaker detection looks wrong (fewer speakers than characters, a child merged with an adult, a line given to the wrong person): read the lines, work out who says each one from the story, then fix them with set_speaker_lines before set_speaker_voices.",
"inputSchema": {
"type": "object",
"required": [
"job_guid"
],
"properties": {
"job_guid": {
"type": "string",
"description": "job_guid of one language from localize_video."
}
},
"additionalProperties": false
},
"annotations": {
"title": "List subtitle lines with their speaker",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}For a multi_speaker localize_video job that has not started voicing yet (e.g. WaitingSpeakerVoices): move lines to another speaker. Send only the lines to change; a new speaker number (e.g. "2" when only 0 and 1 exist) adds a character. Applies to every language of the same video that has not started voicing. The job does not continue: call set_speaker_voices afterwards (include a voice for any new speaker).
| Parameter | Type | Description |
|---|---|---|
| lines * | array | |
| job_guid * | string | job_guid of one language from localize_video. |
{
"name": "set_speaker_lines",
"title": "Fix the speaker of subtitle lines",
"description": "For a multi_speaker localize_video job that has not started voicing yet (e.g. WaitingSpeakerVoices): move lines to another speaker. Send only the lines to change; a new speaker number (e.g. \"2\" when only 0 and 1 exist) adds a character. Applies to every language of the same video that has not started voicing. The job does not continue: call set_speaker_voices afterwards (include a voice for any new speaker).",
"inputSchema": {
"type": "object",
"required": [
"job_guid",
"lines"
],
"properties": {
"lines": {
"type": "array",
"items": {
"type": "object",
"required": [
"block_id",
"speaker"
],
"properties": {
"speaker": {
"type": "string",
"description": "Speaker number, e.g. \"0\", \"1\", or a new one."
},
"block_id": {
"type": "integer",
"description": "block_id from get_speaker_lines."
}
},
"additionalProperties": false
},
"maxItems": 2000,
"minItems": 1
},
"job_guid": {
"type": "string",
"description": "job_guid of one language from localize_video."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Fix the speaker of subtitle lines",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}Check where the user can publish a finished video: which platforms this site offers (YouTube, X), which of the user's accounts are connected, today's YouTube limit, the credit cost of an X post and the user's credits. Call this before offering to publish and before publish_video. If nothing is connected, give the user `connect_url` (connecting needs a browser sign-in) and call this again when they say it is done.
No parameters.
{
"name": "get_publishing_status",
"title": "Publishing accounts and limits",
"description": "Check where the user can publish a finished video: which platforms this site offers (YouTube, X), which of the user's accounts are connected, today's YouTube limit, the credit cost of an X post and the user's credits. Call this before offering to publish and before publish_video. If nothing is connected, give the user `connect_url` (connecting needs a browser sign-in) and call this again when they say it is done.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"annotations": {
"title": "Publishing accounts and limits",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Post a finished video to one of the user's connected accounts. Only call after the user explicitly agreed to publish and confirmed the title (YouTube) or post text (X): this posts publicly on their behalf. YouTube: posted right away, free, needs `title`; set `privacy` (default public). X: posted now or at `scheduled_at`, needs `text` (max 280 characters, links count as 23); costs credits charged only when the post goes out - tell the user the cost from get_publishing_status first. `video_url` must be a TTSForFree link: final_video_url from get_localization_status, or public_url of a video uploaded with create_upload_url.
| Parameter | Type | Description |
|---|---|---|
| tags | string | YouTube tags, comma separated. |
| text | string | X post text. |
| title | string | YouTube title (no < or >). |
| privacy | string | YouTube visibility. Default public. |
| platform | string | Use when the user has exactly one account on that platform. |
| video_url * | string | TTSForFree video link (final_video_url or public_url). |
| account_id | integer | account_id from get_publishing_status. Required when several accounts share a platform. |
| description | string | YouTube description. |
| scheduled_at | string |
The user's recent YouTube / X posts made through TTSForFree, newest first: status (scheduled, uploading, posted, failed, cancelled), the live post_url once posted, the scheduled time and any error message. Use it after publish_video to report the live link.
| Parameter | Type | Description |
|---|---|---|
| limit | integer |
{
"name": "list_published_posts",
"title": "Recent published and scheduled posts",
"description": "The user's recent YouTube / X posts made through TTSForFree, newest first: status (scheduled, uploading, posted, failed, cancelled), the live post_url once posted, the scheduled time and any error message. Use it after publish_video to report the live link.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 50,
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Recent published and scheduled posts",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Cancel a post that is still scheduled (or failed) so it will not be published. A post that is already uploading or posted cannot be cancelled. No credits are charged for cancelled posts.
| Parameter | Type | Description |
|---|---|---|
| post_id * | integer |
{
"name": "cancel_scheduled_post",
"title": "Cancel a scheduled post",
"description": "Cancel a post that is still scheduled (or failed) so it will not be published. A post that is already uploading or posted cannot be cancelled. No credits are charged for cancelled posts.",
"inputSchema": {
"type": "object",
"required": [
"post_id"
],
"properties": {
"post_id": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"title": "Cancel a scheduled post",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": true
}
}TTSForFree turns text into natural speech (thousands of AI voices, 100+ languages) and returns hosted MP3 URLs. Rules: 1. Voice first. If the user did not name a voice: call list_favorite_voices and list_my_custom_voices, then list_voices(language). Always pass the exact `voice` token (v1:...) you received; never build or edit tokens. 2. Pick the tool by who controls the timeline: - text_to_speech: one voice, the audio length may follow the speech (narration, articles, lessons, a new video where scenes can follow the audio). - multi_voice_to_speech: several speakers in order, no fixed timestamps (podcast, dialogue, interview). - srt_to_speech: an existing video or subtitle timeline must be kept (voiceover, dubbing, translated subtitles). Cues start at their timestamps and speed auto-fits each cue. 3. Jobs are asynchronous. If a result says PENDING, call get_job_status with the same job_id and job_type; do not create the job again and never invent or fetch an audio_url before SUCCESS. 4. Credits are real money for the user. For long scripts or many segments call get_account_status first, tell the user the approximate size, and avoid duplicate jobs (check list_recent_jobs when retrying). 5. Video editing: write subtitles with accurate start/end times (one sentence per cue, cue duration >= ~1s per 15 characters), call srt_to_speech, then mux the MP3 with ffmpeg using the commands returned in `video_merge`. The MP3 timeline starts at 00:00 of the video. 6. Show the final audio_url to the user as a link. Report tool errors verbatim; on 429 wait and retry later instead of looping. 7. Video or audio files: create_upload_url, then PUT the file (curl -T), then use public_url. transcribe_media returns the SRT; localize_video dubs a whole video into several languages at once (one audio_url per language for YouTube multi-language audio, plus a dubbed video). YouTube or other external links are never downloaded: ask the user for the original file. If you cannot run commands, ask them to upload on ttsforfree.com and paste the file link. Several characters talking (drama, film, interview)? Use localize_video with multi_speaker = true so every character gets its own voice: when the job reports waiting_speaker_voices, suggest a voice per speaker from the sample lines, confirm with the user and call set_speaker_voices. Fewer speakers than characters, or a line on the wrong person? get_speaker_lines, then set_speaker_lines to fix them first. 8. Publishing. When a video is finished (final_video_url from get_localization_status, or a video the user rendered and uploaded with create_upload_url), call get_publishing_status and offer to publish it to the platforms listed there (YouTube, X) - offer once, do not insist. If an account is connected: propose a title (YouTube) or post text (X), get the user's explicit OK, then call publish_video; YouTube posts right away, X can post now or at a time the user chooses and costs credits (say the cost first). If no account is connected: give the user connect_url to connect YouTube or X in their browser, then continue when they confirm. Never publish without the user's confirmation, and report the live link from list_published_posts. NOTE: Sign-in required. Ask the user to connect their TTSForFree account: in Claude open Settings > Connectors > TTSForFree and click Connect (free account at https://ttsforfree.com). Scripts and agents can instead send the header X-API-Key: YOUR_API_KEY (key from https://ttsforfree.com/en/profile/). Voice browsing (list_languages, list_voices, get_voice_details) works without sign-in.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
{
"name": "srt_to_speech",
"title": "Subtitles to speech (video voiceover / dubbing)",
"description": "Create ONE MP3 that follows a subtitle timeline: every cue starts at its timestamp and speech speed auto-fits the cue duration. Use for video voiceover, dubbing translated subtitles, YouTube localization, tutorials and any edit where audio must line up with existing video. Pass either raw `srt` (SRT or WebVTT text) or `segments` with start_ms/end_ms. For several speakers set `speaker_voices` and prefix cue text with '[Name]' or 'Name:'. The resulting MP3 starts at 00:00 of the video, so it can be muxed directly with ffmpeg (commands are returned). Consumes credits.",
"inputSchema": {
"type": "object",
"properties": {
"srt": {
"type": "string",
"description": "Full SRT or WebVTT content."
},
"voice": {
"type": "string",
"description": "Default voice token for cues without a speaker/voice."
},
"segments": {
"type": "array",
"items": {
"type": "object",
"required": [
"text",
"start_ms",
"end_ms"
],
"properties": {
"text": {
"type": "string",
"minLength": 1
},
"speed": {
"type": "number",
"maximum": 2.5,
"minimum": 0.5
},
"voice": {
"type": "string",
"description": "Optional per-segment voice token; defaults to `voice`."
},
"end_ms": {
"type": "integer",
"minimum": 1
},
"start_ms": {
"type": "integer",
"minimum": 0
}
},
"additionalProperties": false
},
"description": "Alternative to srt: timed segments."
},
"wait_seconds": {
"type": "integer",
"default": 25,
"maximum": 50,
"minimum": 0,
"description": "Seconds the server waits for the audio before returning. If the job is still PENDING, call get_job_status later with the returned job_id."
},
"speaker_voices": {
"type": "object",
"description": "Map speaker name -> voice token, e.g. {\"Host\": \"v1:...\", \"Guest\": \"v1:...\"}.",
"additionalProperties": {
"type": "string"
}
},
"max_speech_rate": {
"type": "number",
"default": 1.5,
"maximum": 2.5,
"minimum": 0.8,
"description": "Highest auto-fit speed when a cue is too short for its text."
},
"min_speech_rate": {
"type": "number",
"default": 0.95,
"maximum": 2.5,
"minimum": 0.8,
"description": "Lowest auto-fit speed. Set min = max for a fixed speed."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Subtitles to speech (video voiceover / dubbing)",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}| Keep the original sound (music/effects) under the new voice at this volume in the dubbed video. 0 = remove. |
{
"name": "localize_video",
"title": "Dub a video into other languages",
"description": "Full automatic dubbing of an uploaded video: transcribe once, translate, voice every target language with its own voice and render a dubbed video per language. Each language returns an audio_url (voice track aligned to the original timeline - upload it to YouTube Studio as a multi-language audio track) and a final_video_url. Takes several minutes: returns job_guids immediately; poll get_localization_status. Confirm the cost with estimate_video_localization for long videos. Several characters (drama, film, interview)? Set multi_speaker = true: speakers are detected on the whole video and each one can get its own voice - pass speaker_voices per target if you already know them, otherwise the job pauses with current_step WaitingSpeakerVoices and get_localization_status lists the speakers with sample lines; ask the user which voice fits each character, then call set_speaker_voices.",
"inputSchema": {
"type": "object",
"required": [
"video_url",
"source_language",
"targets"
],
"properties": {
"targets": {
"type": "array",
"items": {
"type": "object",
"required": [
"language",
"voice"
],
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) for that language from list_voices / favorites / custom voices. With multi_speaker it is the default voice for speakers without their own."
},
"language": {
"type": "string",
"description": "Target language code, e.g. en, es, ja."
},
"speaker_voices": {
"type": "object",
"description": "multi_speaker only: voice per speaker for this language, e.g. {\"0\": \"v1:...\", \"1\": \"v1:...\"}.",
"additionalProperties": {
"type": "string"
}
}
},
"additionalProperties": false
},
"maxItems": 20,
"minItems": 1,
"description": "One entry per target language (the server allows 10 per job by default)."
},
"video_url": {
"type": "string",
"description": "public_url from create_upload_url."
},
"multi_speaker": {
"type": "boolean",
"default": false,
"description": "Dub each character with its own voice. Speakers are detected on the whole video (labels 0, 1, 2... in order of appearance)."
},
"source_language": {
"type": "string",
"description": "Spoken language of the video, e.g. vi."
},
"speaker_voice_step": {
"enum": [
"srt",
"translated"
],
"type": "string",
"default": "srt",
"description": "multi_speaker without speaker_voices: pause for voice choice after transcription (srt) or after translation (translated, shows translated sample lines)."
},
"original_audio_volume_percent": {
"type": "integer",
"maximum": 100,
"minimum": 0,
"description": "Keep the original sound (music/effects) under the new voice at this volume in the dubbed video. 0 = remove."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Dub a video into other languages",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}| X only: ISO 8601 time with offset, e.g. 2026-11-20T09:00:00+07:00. Omit to post now. Ask the user for their time zone if unclear. |
{
"name": "publish_video",
"title": "Publish a video to YouTube or X",
"description": "Post a finished video to one of the user's connected accounts. Only call after the user explicitly agreed to publish and confirmed the title (YouTube) or post text (X): this posts publicly on their behalf. YouTube: posted right away, free, needs `title`; set `privacy` (default public). X: posted now or at `scheduled_at`, needs `text` (max 280 characters, links count as 23); costs credits charged only when the post goes out - tell the user the cost from get_publishing_status first. `video_url` must be a TTSForFree link: final_video_url from get_localization_status, or public_url of a video uploaded with create_upload_url.",
"inputSchema": {
"type": "object",
"required": [
"video_url"
],
"properties": {
"tags": {
"type": "string",
"description": "YouTube tags, comma separated."
},
"text": {
"type": "string",
"description": "X post text."
},
"title": {
"type": "string",
"maxLength": 100,
"description": "YouTube title (no < or >)."
},
"privacy": {
"enum": [
"public",
"unlisted",
"private"
],
"type": "string",
"description": "YouTube visibility. Default public."
},
"platform": {
"enum": [
"youtube",
"x"
],
"type": "string",
"description": "Use when the user has exactly one account on that platform."
},
"video_url": {
"type": "string",
"description": "TTSForFree video link (final_video_url or public_url)."
},
"account_id": {
"type": "integer",
"description": "account_id from get_publishing_status. Required when several accounts share a platform."
},
"description": {
"type": "string",
"maxLength": 5000,
"description": "YouTube description."
},
"scheduled_at": {
"type": "string",
"description": "X only: ISO 8601 time with offset, e.g. 2026-11-20T09:00:00+07:00. Omit to post now. Ask the user for their time zone if unclear."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Publish a video to YouTube or X",
"readOnlyHint": false,
"openWorldHint": false,
"idempotentHint": false,
"destructiveHint": false
}
}