Audio

Text to speech

Turn text into natural-sounding audio.

POST /v1/audio/speech

Generates spoken audio from text. The endpoint follows the OpenAI Audio API (audio.speech), so the official OpenAI SDKs work unchanged with base_url set to https://rutoken.ai/v1. Typical models are tts-1, tts-1-hd and gpt-4o-mini-tts. The response body is the audio file itself, not JSON.

Authentication

Send your key in the Authorization: Bearer sk-xxxx header.

Request body

Parameter	Type	Required	Description
`model`	string	Yes	TTS model ID, e.g. `tts-1`, `gpt-4o-mini-tts`.
`input`	string	Yes	Text to speak, up to 4096 characters.
`voice`	string	Yes	Voice, e.g. `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`. Available voices depend on the model.
`instructions`	string	No	Tone and style instructions (`gpt-4o-mini-tts` only), e.g. "Speak in a calm, friendly voice".
`response_format`	string	No	`mp3` (default), `opus`, `aac`, `flac`, `wav` or `pcm`.
`speed`	number	No	Playback speed from `0.25` to `4.0`. Default `1.0`.
`stream_format`	string	No	`audio` (default) or `sse`, for models that support streaming.

Request example

cURL

curl https://rutoken.ai/v1/audio/speech \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "gpt-4o-mini-tts",
    "input": "Hello! Your order has been shipped and will arrive tomorrow.",
    "voice": "coral",
    "instructions": "Speak in a cheerful and positive tone.",
    "response_format": "mp3"
  }' \
  --output speech.mp3

Python

from openai import OpenAI

client = OpenAI(base_url="https://rutoken.ai/v1", api_key="sk-xxxx")
with client.audio.speech.with_streaming_response.create(
    model="gpt-4o-mini-tts",
    voice="coral",
    input="Hello! Your order has been shipped and will arrive tomorrow.",
    instructions="Speak in a cheerful and positive tone.",
) as resp:
    resp.stream_to_file("speech.mp3")

Node.js

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://rutoken.ai/v1", apiKey: "sk-xxxx" });
const resp = await client.audio.speech.create({
  model: "gpt-4o-mini-tts",
  voice: "coral",
  input: "Hello! Your order has been shipped and will arrive tomorrow.",
  instructions: "Speak in a cheerful and positive tone.",
});
fs.writeFileSync("speech.mp3", Buffer.from(await resp.arrayBuffer()));

Response

On success the response is the binary audio stream with a matching Content-Type header (for example audio/mpeg for mp3). Save it to a file or play it directly.

On failure the gateway returns a JSON error:

json

{
  "error": {
    "message": "Invalid value for 'voice'.",
    "type": "invalid_request_error",
    "param": null,
    "code": null
  }
}

Notes

If model is omitted, the gateway routes the request as tts-1.
Check the Model Square for the price of each TTS model.