Skip to main content
Sends raw audio bytes back in the response — no polling, no follow-up requests.

Quickstart

Request body

string
required
TTS model ID (e.g. eleven_v3, cartesia-sonic-2).
string
required
Text to synthesize.
string
Provider-specific voice ID. Falls back to the model’s default voice when omitted.
"mp3" | "wav" | "opus" | "flac" | "aac"
default:"\"mp3\""
Container / codec for the returned audio.
integer
default:"24000"
Output sample rate in Hz.
number
default:"1.0"
Playback speed multiplier where supported.

Response

The body is the raw audio file. Inspect Content-Type to confirm the codec:

Streaming

For low-latency playback, open a WebSocket to wss://gateway.llm-stats.com/v1/tts/stream and follow the protocol described in the dashboard’s TTS playground. The HTTP endpoint above is the right choice for short, batch synthesis.

Errors

Failures use the shared error envelope. Common ones: