Generate AI voices, text-to-speech, subtitles, transcription, and video localization.
Scored across 25 tools
The tools are generally well-separated by resource and action: three distinct speech-rendering modes, separate voice-listing variants, and distinct status checkers per job type. The only mild overlap is between get_job_status and get_job_detail (both may cover multi-voice/SRT jobs), which descriptions mostly disambiguate but could still cause hesitation.
All names use snake_case, and most follow a clear verb_noun pattern (list_voices, get_job_status, publish_video). A handful of generation tools use a noun_to_speech form (text_to_speech, srt_to_speech), which is a deliberate and readable sub-pattern rather than a violation.
25 tools is at the upper edge but reasonable for a platform spanning speech synthesis, transcription, video localization, voice catalog management, and social publishing. Each tool maps to a concrete operation, though the surface is heavy enough that a few status/list tools could potentially be consolidated.
The surface covers most lifecycle needs: voice discovery and favorites, custom voice creation via prompt, three speech modes, transcription, localization, publishing, and job status/listing. Minor gaps include no tool to create a cloned voice from an audio sample (only mentioned in list_my_custom_voices) and no delete/update operations for custom voices or speech jobs.
Save a voice to the user's favorites (only when the user asks).
Inputs: voice (required).
Cancel a post that is still scheduled (or failed) so it will not be published.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.
Inputs: post_id (required).
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.
Inputs: file_name (required), file_size_bytes.
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.
Inputs: gender (required), prompt (required), display_name (required), language_code (required).
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.
Inputs: targets (required), source_language (required), video_url, duration_seconds.
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.
Inputs: no named parameters.
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 per segment; measure each file's duration in the renderer).
Inputs: job_id (required).
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.
Inputs: job_id (required), job_type (required), 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.
Inputs: job_guids (required), wait_seconds.
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.
Inputs: no named parameters.
Check a transcribe_media job and get its SRT once finished.
Inputs: job_id (required), wait_seconds.
Get full metadata for one voice token: persona, use case, accent, pitch, styles, preview audio and credit cost.
Inputs: voice (required).
List the voices the user marked as favorites, in their saved order. Check this first when the user did not name a voice.
Inputs: no named parameters.
List every language supported by TTSForFree text-to-speech. Returns language codes to pass to list_voices.
Inputs: no named parameters.
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.
Inputs: no named parameters.
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.
Inputs: limit.
List the user's most recent speech jobs with status and audio URLs, to reuse earlier audio instead of paying again.
Inputs: limit, job_type.
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.
Inputs: language (required), limit, query, gender, +2 more.
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.
Inputs: targets (required), video_url (required), source_language (required), original_audio_volume_percent.
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.
Inputs: segments (required), wait_seconds.
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.
Inputs: video_url (required), tags, text, title, +5 more.
Remove a voice from the user's favorites (only when the user asks).
Inputs: voice (required).
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.
Inputs: srt, voice, segments, wait_seconds, +3 more.
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.
Inputs: text (required), voice (required), pitch, 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.
Inputs: language (required), media_url (required), wait_seconds.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Add one secure layer between your agents and this server.
