# Gemini 3.8 Flash TTS (`google/gemini-3.8-flash-tts`): API

> google/gemini-3.8-flash-tts is a text-to-speech model from Google you can call on the OceanToken API.

Endpoint: `POST https://api.oceantoken.ai/v1/audio/speech`. Auth: `Authorization: Bearer $OCEANTOKEN_API_KEY`. OpenAI-compatible; the OpenAI SDKs work with base URL https://api.oceantoken.ai/v1.

## Request parameters

- `model` (string; required): This model's ID.
- `input` (string; required): The text to read.
- `voice` (string; required): One of this model's voices (see the Speech guide).
- `response_format` (string; mp3, wav, opus, aac, flac, pcm, url): Audio format; `url` returns a link instead of the audio.
- `speed` (number; 0.25 to 4; default 1): Pace, on models that support it.
- `instructions` (string): Tone notes such as "calm, slow", on models that support them.

## Example: Basic

```bash
curl https://api.oceantoken.ai/v1/audio/speech \
  -H "Authorization: Bearer $OCEANTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google/gemini-3.8-flash-tts",
  "input": "Welcome aboard.",
  "voice": "VOICE_NAME",
  "response_format": "mp3"
}' --output speech.mp3
```

```python
import os
from openai import OpenAI

client = OpenAI(base_url="https://api.oceantoken.ai/v1", api_key=os.environ["OCEANTOKEN_API_KEY"])
audio = client.audio.speech.create(
    model="google/gemini-3.8-flash-tts",
    input="Welcome aboard.",
    voice="VOICE_NAME",
    response_format="mp3",
)
audio.write_to_file("speech.mp3")
```

## Response

- `(body)` (binary): The audio file.

## More

- Model page: https://docs.oceantoken.ai/models/google/gemini-3.8-flash-tts
- This spec as JSON (with a JSON Schema of the request): https://docs.oceantoken.ai/models/google/gemini-3.8-flash-tts/spec.json
- Guide: https://docs.oceantoken.ai/guides/audio
- All models: https://docs.oceantoken.ai/llms.txt