v1

latestOpenAPI 3.1.0Proprietary2026-08-0492426.9 KB

Speech

Synthesize speech from text

Render the given text as speech (24 kHz mono WAV) in the requested speaker's voice.

post/v1/tts

textstring required

Text to speak.

speakerstring

Speaker role to render the text as (one of the model's speakers; see GET /v1/models).

modelstring nullable

Public model id (see GET /v1/models). Omit/null for the default model.

{
  "text": "Hey there! How are you doing today?",
  "model": "kalpa-tts-beta-v0.1"
}

Successful Response

request_idstring required

Correlation id; identical to the X-Request-ID response header.

modelstring required

Resolved public model id that served the request.

textstring required

The text that was spoken (echoes the request).

metaobject

Backend-specific diagnostics (latency, frames, …).

{
  "audio": {
    "sample_rate": 24000
  }
}