Text-to-Speech (TTS)

Generate natural speech from text using the MCP server.

Available Tools

Tool	Description
`sixtydb_tts_synthesize`	Convert text to speech and return the audio
`sixtydb_tts_logs`	View TTS generation history
`sixtydb_tts_get`	Get specific generation details

Synthesize Speech

Convert text to audio:

{
  "text": "Hello, world!",
  "voice_id": "voice_abc123",
  "speed": 1.0
}

Response: the audio clip itself (WAV, 24 kHz, mono) plus a summary:

## Speech generated

- **Voice**: voice_abc123
- **Characters**: 13 (1 credit each)
- **Duration**: 1.2s
- **Format**: WAV, 24 kHz mono, 57 KB
- **Audio enhancement**: on

The tool calls POST /tts-synthesize and charges 1 credit per character.

Parameters

Parameter	Type	Default	Description
`text`	string	Required	Text to synthesize
`voice_id`	string	Required	Voice to use
`speed`	number	1	Speech speed (0.25-2.0)
`stability`	number	50	Voice stability (0-100)
`similarity`	number	75	Voice similarity (0-100)
`audio_enhance`	boolean	true	Polish the generated audio. Set `false` to skip it for the fastest result
`output_format`	string	wav	Only WAV is produced. `mp3` and `ogg` are accepted for compatibility but the clip is still returned as WAV
`response_format`	string	markdown	Format of the summary (`markdown` or `json`)

Usage in Claude

You: Convert "Welcome to our podcast" to speech
You: Generate speech with faster speed
You: Use a Spanish voice for this text

Supported Languages

English (US, UK, Australian)
Spanish, French, German, Italian
Portuguese, Japanese, Korean, Chinese
And 30+ more languages

Voices - Browse available voices
STT - Speech-to-text