TTSForFree

Generate AI voices, convert text to speech, create multi-voice audio, convert SRT subtitles to speech, transcribe media, and localize videos.

GitHub

Gehosteter MCP-Server

npx add-mcp 'https://api.ttsforfree.com/mcp'

Installiert in Claude Code, Codex, Cursor und mehr

Dokumentation

TTSForFree MCP server

Text-to-speech, multi-voice podcasts, subtitle voiceovers, transcription and video dubbing for Claude and any other MCP client. Thousands of AI voices in 100+ languages, returned as hosted MP3 URLs.

Server URL: https://api.ttsforfree.com/mcp (Streamable HTTP, remote, nothing to install)
Sign-in: OAuth. Click Connect and sign in to TTSForFree. No API key needed. An API key (X-API-Key header) also works for scripts and agents.
Registry: io.github.CalmNguyen/ttsforfree
Website: ttsforfree.com · setup guide: ttsforfree.com/en/claude-tts-connector

A free plan is included. Paid generation uses your TTSForFree credits.

Connect

Claude (claude.ai, Desktop, mobile)

Settings → Connectors → Add custom connector
URL: https://api.ttsforfree.com/mcp
Click Connect, sign in to TTSForFree and allow access.

Claude Code

claude mcp add --transport http ttsforfree https://api.ttsforfree.com/mcp

Then run /mcp → ttsforfree → Authenticate. With an API key instead:

claude mcp add --transport http ttsforfree https://api.ttsforfree.com/mcp \
  --header "X-API-Key: YOUR_API_KEY"

Cursor, VS Code and other clients

{
  "mcpServers": {
    "ttsforfree": {
      "url": "https://api.ttsforfree.com/mcp"
    }
  }
}

Add "headers": { "X-API-Key": "YOUR_API_KEY" } if the client does not support OAuth. Get an API key at ttsforfree.com/en/profile.

Claude API (MCP connector)

curl https://api.anthropic.com/v1/messages \
  -H "x-api-key: $ANTHROPIC_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "anthropic-beta: mcp-client-2025-11-20" \
  -H "content-type: application/json" \
  -d '{
    "model": "claude-opus-5-5",
    "max_tokens": 2048,
    "mcp_servers": [{
      "type": "url",
      "name": "ttsforfree",
      "url": "https://api.ttsforfree.com/mcp",
      "authorization_token": "YOUR_TTSFORFREE_API_KEY"
    }],
    "tools": [{ "type": "mcp_toolset", "mcp_server_name": "ttsforfree" }],
    "messages": [{ "role": "user", "content": "Read this in a warm British voice: Welcome to our channel!" }]
  }'

What you can ask

Ask Claude	Tools it uses
"Read this lesson in a calm British voice from my favorites."	`list_favorite_voices` → `text_to_speech`
"Turn this article into a 2-host podcast, one MP3."	`multi_voice_to_speech` → `get_job_detail`
"Translate this SRT to Spanish, keep the timestamps, voice it, give me the ffmpeg command."	`srt_to_speech` → `get_job_status`
"Transcribe this video into an SRT file."	`create_upload_url` → `transcribe_media`
"Dub this video into Vietnamese, Spanish and Japanese for YouTube. Cost first."	`create_upload_url` → `estimate_video_localization` → `localize_video` → `get_localization_status`
"Make me a young male voice that reviews stories, southern Vietnamese accent."	`design_custom_voice`

Video walkthroughs: ttsforfree.com/en/claude-tts-connector.

Tools (21)

Tool	Type	What it does
`list_languages`	read	All supported languages and their codes.
`list_voices`	read	Search voices by language, gender, provider and keywords ("warm narrator").
`get_voice_details`	read	Persona, use case, accent, styles, preview audio and credit cost of one voice.
`list_favorite_voices`	read	The user's favorite voices, in saved order.
`list_my_custom_voices`	read	Personal voices from Voice Design / Voice Clone and the remaining quota.
`add_favorite_voice`	write	Save a voice to favorites.
`remove_favorite_voice`	write	Remove a voice from favorites.
`design_custom_voice`	write	Create a new personal voice from a text description.
`get_account_status`	read	Plan, remaining credits, per-request limits and API rate limits.
`text_to_speech`	job	One text + one voice → MP3 (narration, articles, lessons).
`multi_voice_to_speech`	job	Ordered segments with different voices → one MP3 (podcast, dialogue).
`srt_to_speech`	job	SRT/WebVTT or timed segments → timeline-aligned MP3 + ffmpeg merge commands.
`get_job_status`	read	Poll a job until SUCCESS and get the audio URL.
`list_recent_jobs`	read	Recent jobs with audio URLs, to reuse instead of paying twice.
`get_job_detail`	read	Per-segment audio of a multi-voice/SRT job (for Remotion and captions).
`create_upload_url`	write	One-time upload URL for a local video/audio file (PUT, up to 2 GB).
`transcribe_media`	job	Video/audio → timestamped SRT (speech-to-text).
`get_transcription`	read	Status and SRT of a transcription.
`estimate_video_localization`	read	Credit estimate to dub a video into several languages.
`localize_video`	job	Dub one video into many languages: audio track + dubbed video per language.
`get_localization_status`	read	Progress and results (audio URL for YouTube, dubbed video, SRT) per language.

job tools are asynchronous: they return a job_id, and the client polls the matching status tool until SUCCESS.

Prompts: youtube_multi_language_audio, video_voiceover, podcast_episode, narrate_text.

Privacy and data

OAuth access is scoped to your TTSForFree account and can be revoked any time from your TTSForFree profile (Connected apps).
Text, subtitles and uploaded media are processed only to produce the audio, subtitles or video you asked for.
Privacy policy: ttsforfree.com/en/privacy-policy

Support

Open an issue in this repository or contact us via ttsforfree.com/en/contact.

Registry metadata

server.json is the entry published to the MCP Registry. To publish an update, bump version in server.json and push a tag vX.Y.Z (or run the Publish to MCP Registry workflow manually). The workflow signs in with GitHub OIDC, so no secret is needed.