Skip to main content
POST https://gateway.llm-stats.com/v1/tts/synthesize
Sends raw audio bytes back in the response — no polling, no follow-up requests.

​
Quickstart

import requests

response = requests.post(
    "https://gateway.llm-stats.com/v1/tts/synthesize",
    headers={"Authorization": "Bearer YOUR_API_KEY"},
    json={
        "model_id": "eleven_v3",
        "text": "Hello, this is a test.",
        "format": "mp3",
        "sample_rate": 24000,
    },
)

with open("output.mp3", "wb") as f:
    f.write(response.content)

​
Request body

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

​
Response

The body is the raw audio file. Inspect Content-Type to confirm the codec:
formatContent-Type
mp3audio/mpeg
wavaudio/wav
opusaudio/opus
flacaudio/flac
aacaudio/aac

​
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:
Statuserror.codeWhen
400invalid_inputMissing text, unsupported format, …
401unauthenticatedMissing or invalid API key.
402insufficient_quotaOut of credit.
429rate_limitedQuota exceeded — back off using Retry-After.
502provider_unavailableEvery TTS provider for this model errored.