# tts MCP server

Hosted pay-per-use TTS: 54 neural voices, 9 languages incl. Brazilian Portuguese. $10 free credits.

## Links
- Registry page: https://www.getdrio.com/mcp/com-brainiall-tts
- Repository: https://github.com/fasuizu-br/brainiall-tts-mcp
- Website: https://brainiall.com

## Install
- Endpoint: https://api.brainiall.com/mcp/tts/mcp
- Auth: Auth required by registry metadata

## Setup notes
- Remote header: Authorization (required; secret)
- The upstream registry signals required auth or secrets.
- Remote endpoint: https://api.brainiall.com/mcp/tts/mcp
- Header: Authorization

## Tools
- synthesize_speech (Synthesize Speech) - Convert text to natural-sounding speech.

Returns WAV audio (16-bit PCM, 24 kHz mono) synthesized with neural voices.
54 voices across 9 languages -- including 3 native Brazilian Portuguese
voices (pf_dora, pm_alex, pm_santa). Usage is metered per character.

Args:
    text: Text to convert to speech (max 5000 characters per request).
    language: Language code; selects the default voice when no voice is given.
    voice: Explicit voice ID (see list_voices). Overrides language.
    speed: Speech speed multiplier, 0.5-2.0.
    output_format: 'audio' for playable MCP audio content, 'base64_json'
        for a JSON object with the base64-encoded WAV and metadata.

Returns:
    MCP audio content (audio/wav), or when output_format='base64_json' a
    dict with keys:
        - audio_base64 (str): Base64-encoded WAV bytes
        - mime_type (str): 'audio/wav'
        - voice (str): Voice used
        - characters (int): Characters billed
        - estimated_cost_usd (float): Estimated cost of this request Endpoint: https://api.brainiall.com/mcp/tts/mcp
- list_voices (List Voices) - List available TTS voices with metadata.

54 neural voices across 9 languages. Each voice has an ID (used in
synthesize_speech), display name, gender, accent and quality grade.

Args:
    language: Optional language filter (e.g. 'pt-br', 'en-us').

Returns:
    dict with keys:
        - voices (list): Each with id, name, gender, accent, lang, grade
        - count (int): Number of voices returned Endpoint: https://api.brainiall.com/mcp/tts/mcp
- check_tts_service (Check TTS Service) - Check health status of the TTS API service.

Returns:
    dict with keys:
        - status (str): 'healthy' or error state Endpoint: https://api.brainiall.com/mcp/tts/mcp

## Resources
- tts://voices - Quick reference of voice IDs grouped by language. MIME type: text/plain
- tts://pricing - Pricing information for TTS API calls. MIME type: text/plain

## Prompts
- narrate_text - Narrate a piece of text with the best-fitting voice.

Args:
    text: The text to narrate.
    language: The language of the text (default 'pt'). Arguments: text, language

## Metadata
- Owner: com.brainiall
- Version: 1.0.0
- Runtime: Streamable Http
- Transports: HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 10, 2026
- Source: https://registry.modelcontextprotocol.io