v2

latestOpenAPI 3.1.02026-08-01302833.9 KB
Unified Agent APIs

Unified Tts

Unified text-to-speech.

Converts text to audio. Deepgram Aura is the primary provider with 105+ voice models across 7 languages. ElevenLabs is the fallback with premium pre-defined voices. Returns base64-encoded audio.

For low-latency streaming, use a direct WebSocket connection to the provider. This endpoint is for batch synthesis (generate audio from text, get result).

post/v1/speech/synthesize

Request body

textstring required
voice_modelstring nullable
voice_idstring nullable
providerstring nullable
stabilitynumber
similarity_boostnumber

Response

Successful Response

{"stackTrail":"paths:/v1/speech/synthesize:post:responses:200:content:application/json:schema","oasType":"schema","type":"unknown"}