TTSForFree
Generate AI voices, text-to-speech, subtitles, transcription, and video localization.
¿Debería usar esto?
Calidad y seguridad
Hallazgos (4)
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domainen create_upload_url
- LOWTool 'get_localization_status' description lacks action verben get_localization_status
- LOWTool 'create_upload_url' suggests web access but openWorldHint=falseen create_upload_url
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"ttsforfree": {
"url": "https://api.ttsforfree.com/mcp"
}
}
}Puntos de conexión remotos
https://api.ttsforfree.com/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (21)
🟢list_languages
List every language supported by TTSForFree text-to-speech. Returns language codes to pass to list_voices.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢list_voices(language, gender, provider, query, only_usable, ...)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"language": {
"type": "string",
"description": "Language code from list_languages, e.g. en, vi, es, ja."
},
"gender": {
"type": "string",
"enum": [
"male",
"female"
]
},
"provider": {
"type": "string",
"enum": [
"Google",
"Azure",
"Gemini",
"OpenAI",
"FPT"
],
"description": "Optional voice engine filter. Gemini/OpenAI voices are the most expressive."
},
"query": {
"type": "string",
"description": "Optional keywords matched against name, style, persona and use case, e.g. 'warm narrator', 'news', 'young'."
},
"only_usable": {
"type": "boolean",
"default": true,
"description": "Hide voices the current plan cannot use."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"default": 25
}
},
"required": [
"language"
],
"additionalProperties": false
}🟢get_voice_details(voice)
Get full metadata for one voice token: persona, use case, accent, pitch, styles, preview audio and credit cost.
Esquema de entrada
{
"type": "object",
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_voices, favorites or custom voices."
}
},
"required": [
"voice"
],
"additionalProperties": false
}🟢list_my_custom_voices
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.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢list_favorite_voices
List the voices the user marked as favorites, in their saved order. Check this first when the user did not name a voice.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟡add_favorite_voice(voice)
Save a voice to the user's favorites (only when the user asks).
Esquema de entrada
{
"type": "object",
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_voices."
}
},
"required": [
"voice"
],
"additionalProperties": false
}🔴remove_favorite_voice(voice)
Remove a voice from the user's favorites (only when the user asks).
Esquema de entrada
{
"type": "object",
"properties": {
"voice": {
"type": "string",
"description": "Voice token (v1:...) from list_favorite_voices."
}
},
"required": [
"voice"
],
"additionalProperties": false
}🟡design_custom_voice(display_name, gender, language_code, prompt)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"display_name": {
"type": "string",
"minLength": 1,
"maxLength": 60
},
"gender": {
"type": "string",
"enum": [
"male",
"female"
]
},
"language_code": {
"type": "string",
"description": "BCP-47 locale, e.g. en-US, vi-VN."
},
"prompt": {
"type": "string",
"minLength": 20,
"maxLength": 1500,
"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.'"
}
},
"required": [
"display_name",
"gender",
"language_code",
"prompt"
],
"additionalProperties": false
}🟢get_account_status
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.
Esquema de entrada
{
"type": "object",
"properties": {},
"additionalProperties": false
}⚪text_to_speech(text, voice, pitch, wait_seconds)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1,
"description": "Text to read. Plain text; long text is split and merged automatically."
},
"voice": {
"type": "string",
"description": "Voice token (v1:...)."
},
"pitch": {
"type": "number",
"minimum": -100,
"maximum": 100,
"default": 0,
"description": "Only some providers support pitch."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"text",
"voice"
],
"additionalProperties": false
}⚪multi_voice_to_speech(segments, wait_seconds)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"segments": {
"type": "array",
"minItems": 1,
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1
},
"voice": {
"type": "string",
"description": "Voice token (v1:...)."
},
"speed": {
"type": "number",
"minimum": 0.5,
"maximum": 2.5,
"default": 1
},
"volume": {
"type": "number",
"minimum": 0,
"maximum": 2,
"default": 1
},
"pause_after_ms": {
"type": "integer",
"minimum": 0,
"maximum": 10000,
"default": 300,
"description": "Silence after this segment."
}
},
"required": [
"text",
"voice"
],
"additionalProperties": false
}
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"segments"
],
"additionalProperties": false
}🟡srt_to_speech(srt, segments, voice, speaker_voices, min_speech_rate, ...)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"srt": {
"type": "string",
"description": "Full SRT or WebVTT content."
},
"segments": {
"type": "array",
"description": "Alternative to srt: timed segments.",
"items": {
"type": "object",
"properties": {
"text": {
"type": "string",
"minLength": 1
},
"start_ms": {
"type": "integer",
"minimum": 0
},
"end_ms": {
"type": "integer",
"minimum": 1
},
"voice": {
"type": "string",
"description": "Optional per-segment voice token; defaults to `voice`."
},
"speed": {
"type": "number",
"minimum": 0.5,
"maximum": 2.5
}
},
"required": [
"text",
"start_ms",
"end_ms"
],
"additionalProperties": false
}
},
"voice": {
"type": "string",
"description": "Default voice token for cues without a speaker/voice."
},
"speaker_voices": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"description": "Map speaker name -> voice token, e.g. {\"Host\": \"v1:...\", \"Guest\": \"v1:...\"}."
},
"min_speech_rate": {
"type": "number",
"minimum": 0.8,
"maximum": 2.5,
"default": 0.95,
"description": "Lowest auto-fit speed. Set min = max for a fixed speed."
},
"max_speech_rate": {
"type": "number",
"minimum": 0.8,
"maximum": 2.5,
"default": 1.5,
"description": "Highest auto-fit speed when a cue is too short for its text."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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
}🟢get_job_status(job_id, job_type, wait_seconds)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
},
"job_type": {
"type": "string",
"enum": [
"single",
"multi",
"srt"
],
"description": "single = text_to_speech, multi = multi_voice_to_speech, srt = srt_to_speech."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"job_id",
"job_type"
],
"additionalProperties": false
}🟢list_recent_jobs(job_type, limit)
List the user's most recent speech jobs with status and audio URLs, to reuse earlier audio instead of paying again.
Esquema de entrada
{
"type": "object",
"properties": {
"job_type": {
"type": "string",
"enum": [
"single",
"multi",
"srt"
],
"default": "single"
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"default": 10
}
},
"additionalProperties": false
}🟢get_job_detail(job_id)
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).
Esquema de entrada
{
"type": "object",
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
}
},
"required": [
"job_id"
],
"additionalProperties": false
}🟡create_upload_url(file_name, file_size_bytes)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"file_name": {
"type": "string",
"description": "Original file name with extension, e.g. lesson-01.mp4"
},
"file_size_bytes": {
"type": "integer",
"minimum": 1
}
},
"required": [
"file_name"
],
"additionalProperties": false
}🟢transcribe_media(media_url, language, wait_seconds)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"media_url": {
"type": "string",
"description": "public_url from create_upload_url (or a ttsforfree CDN link)."
},
"language": {
"type": "string",
"description": "Spoken language code, e.g. vi, en, ja."
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"media_url",
"language"
],
"additionalProperties": false
}🟢get_transcription(job_id, wait_seconds)
Check a transcribe_media job and get its SRT once finished.
Esquema de entrada
{
"type": "object",
"properties": {
"job_id": {
"type": "integer",
"minimum": 1
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"job_id"
],
"additionalProperties": false
}🟢estimate_video_localization(video_url, duration_seconds, source_language, targets)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"video_url": {
"type": "string"
},
"duration_seconds": {
"type": "number",
"minimum": 1
},
"source_language": {
"type": "string"
},
"targets": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"description": "One entry per target language (the server allows 10 per job by default).",
"items": {
"type": "object",
"properties": {
"language": {
"type": "string",
"description": "Target language code, e.g. en, es, ja."
},
"voice": {
"type": "string",
"description": "Voice token (v1:...) for that language from list_voices / favorites / custom voices."
}
},
"required": [
"language",
"voice"
],
"additionalProperties": false
}
}
},
"required": [
"source_language",
"targets"
],
"additionalProperties": false
}🟡localize_video(video_url, source_language, targets, original_audio_volume_percent)
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.
Esquema de entrada
{
"type": "object",
"properties": {
"video_url": {
"type": "string",
"description": "public_url from create_upload_url."
},
"source_language": {
"type": "string",
"description": "Spoken language of the video, e.g. vi."
},
"targets": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"description": "One entry per target language (the server allows 10 per job by default).",
"items": {
"type": "object",
"properties": {
"language": {
"type": "string",
"description": "Target language code, e.g. en, es, ja."
},
"voice": {
"type": "string",
"description": "Voice token (v1:...) for that language from list_voices / favorites / custom voices."
}
},
"required": [
"language",
"voice"
],
"additionalProperties": false
}
},
"original_audio_volume_percent": {
"type": "integer",
"minimum": 0,
"maximum": 100,
"description": "Keep the original sound (music/effects) under the new voice at this volume in the dubbed video. 0 = remove."
}
},
"required": [
"video_url",
"source_language",
"targets"
],
"additionalProperties": false
}🟢get_localization_status(job_guids, wait_seconds)
Status of localize_video jobs: current step, and when Completed the dubbed audio_url, final_video_url and translated SRT for each language.
Esquema de entrada
{
"type": "object",
"properties": {
"job_guids": {
"type": "array",
"minItems": 1,
"maxItems": 20,
"items": {
"type": "string"
}
},
"wait_seconds": {
"type": "integer",
"minimum": 0,
"maximum": 50,
"default": 25,
"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."
}
},
"required": [
"job_guids"
],
"additionalProperties": false
}Comunidad
Evidencia