# Audio Speech API — Text to speech

Source: https://ofox.ai/docs/api/openai/audio-speech

Turns text into speech. Compatible with OpenAI's `POST /v1/audio/speech`; the response body is the audio file itself (binary), not JSON.

| Family | Model | Notes |
|---|---|---|
| ElevenLabs | `elevenlabs/eleven_v4` | See [ElevenLabs](https://ofox.ai/docs/develop/models/elevenlabs) |
| Gemini TTS | `google/gemini-3.8-flash-tts` and others | See [Gemini TTS](https://ofox.ai/docs/develop/models/gemini-tts) |

Accepted values for `voice`, `response_format` and other parameters vary by model; the family pages are authoritative.

## Quickstart

- base_url: `https://api.ofox.ai/v1`
- Endpoint: `https://api.ofox.ai/v1/audio/speech`
- Model ID: `google/gemini-3.8-flash-tts`

**Python**

```python filename="speech.py"
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.ofox.ai/v1", api_key=os.environ["OFOX_API_KEY"])

with client.audio.speech.with_streaming_response.create(
    model="google/gemini-3.8-flash-tts",
    voice="Kore",
    input="Hello, and welcome to OfoxAI text to speech.",
    response_format="wav",
) as resp:
    resp.stream_to_file("speech.wav")
```

**cURL**

```bash filename="Terminal"
curl https://api.ofox.ai/v1/audio/speech \
  -H "Authorization: Bearer $OFOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.8-flash-tts",
    "voice": "Kore",
    "input": "Hello, and welcome to OfoxAI text to speech.",
    "response_format": "wav"
  }' \
  --output speech.wav
```

## Request parameters

**model** `string` · required

Model ID; see the table above.

**input** `string` · required

The text to synthesize. An empty value returns 400.

**voice** `string`

The voice. Required for Gemini TTS, where it takes a Google voice name (e.g. `Kore`); for ElevenLabs it takes a voice ID (e.g. `21m00Tcm4TlvDq8ikWAM`). OpenAI voice names (e.g. `alloy`) do not work with either family.

**response_format** `string`

Audio format. Accepted values vary by model: Gemini TTS supports `wav` and `pcm`; ElevenLabs supports `mp3`, `opus`, `wav` and `pcm`. An unsupported format returns 400.

**instructions** `string`

Tone and style instructions, such as "read this in a cheerful tone". Applies to Gemini TTS.

**language_code** `string`

Language code, such as `cmn-CN` (Gemini TTS) or `zh` (ElevenLabs). If omitted, the model infers the language from the text.

**stream_format** `string` · values `sse`

With `sse`, audio chunks are streamed as Server-Sent Events. Applies to Gemini TTS.

**provider_options** `object`

Provider-specific parameters, passed through to the provider, e.g. ElevenLabs' `{"elevenlabs": {"voice_settings": {...}}}`. See each family page.

## Response
On success, HTTP 200 with the audio file as the response body; `Content-Type` matches the format:

| response_format | Content-Type |
|---|---|
| `mp3` | `audio/mpeg` |
| `wav` | `audio/wav` |
| `opus` | `audio/ogg` |
| `pcm` | `audio/L16;rate=<sample rate>;channels=1`, headerless 16-bit PCM |

Write the response body straight to a file. Errors are returned as JSON with `Content-Type` `application/json`, so check the status code first to avoid saving an error message as an audio file.

## Common errors
| HTTP | Error message | Cause | Fix |
|---|---|---|---|
| 400 | `model and input are required.` | `model` is missing, or `input` is empty | Supply the missing parameters |
| 400 | `voice is required for speech completion` | `voice` not sent for Gemini TTS | Pass a voice name, such as `Kore` |
| 400 | `unsupported Gemini response_format: mp3` | The model does not support the chosen format | Use a format listed on the family page |
| 400 | `Request contains an invalid argument.` | The Gemini TTS voice name does not exist | Use a valid voice name |
| 404 | `A voice with voice_id 'alloy' was not found.` | The ElevenLabs voice ID does not exist | Use a valid voice ID |
| 400 `endpoint_not_supported` | `Model 'openai/gpt-5.4' does not support the /v1/audio/speech endpoint on this platform.` | The chosen model is not a speech synthesis model | Use a model from the table above |

For the full list of error codes, see [Error handling](https://ofox.ai/docs/develop/guides/error-handling).