Home / MCP Tools / Tts Voice
Live MCP toolmedia

Tts Voice

Text-to-speech via ElevenLabs.

Text-to-speech via ElevenLabs. BYOK ONLY. The MP3 is stored as a durable Wingman artifact and its URL returned. Returns {ok, audio_url, voice_id, chars}.

Metered access — free-key quota or x402 pay-per-call (USDC on Base). Details at /pricing.

Parameters

ParameterTypeRequiredDescription
textstringrequiredtext to speak (max 5000 chars)
voice_idstringoptionalElevenLabs voice id (default: Rachel)
model_idstringoptionalElevenLabs model (default eleven_multilingual_v2)
api_keystringoptionalyour ElevenLabs key (BYOK, inline)
key_refstringoptionalvault entry holding your ElevenLabs key (BYOK alt)
handlestringoptionalyour handle (BYOK via vault + artifact ownership)
secretstringoptionalyour agent secret

Call it over MCP (JSON-RPC 2.0)

curl -s https://wingmanprotocol.com/mcp \
  -H 'Content-Type: application/json' \
  -H 'Accept: application/json, text/event-stream' \
  -d '{"jsonrpc": "2.0", "id": 1, "method": "tools/call", "params": {"name": "tts_voice", "arguments": {"text": "hello from an agent"}}}'

Or plain HTTP

curl -s https://wingmanprotocol.com/tools/tts_voice \
  -H 'Content-Type: application/json' \
  -d '{"text": "hello from an agent"}'

Try it live

Edit the JSON and run it — this POSTs to https://wingmanprotocol.com/tools/tts_voice from your browser.

Related tools in Media

media
Gen Avatar Video
Async talking-avatar video via HeyGen (text→avatar).
media
Gen Id Portrait
FREE identity-preserving portrait: give ONE face photo (face_url or face_b64) and get a stylized portrait that keeps…
media
Gen Image
Generate an image from a text prompt via FAL Flux.
media
Gen Video
Async text-to-video via FAL (Kling/Veo).
media
Voice Transcribe
Transcribe short audio to text via OpenAI Whisper.