> ## Documentation Index
> Fetch the complete documentation index at: https://docs.ekly.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Gemini TTS

> Google's Gemini text-to-speech model.

Google's Gemini text-to-speech model. Converts text to natural-sounding speech using Gemini's advanced voice synthesis.

| | |
| - | - |
| Model id | `gemini-3.1-flash-tts-preview` |
| Media | audio |
| Submit to | `POST /v1/audio` |
| Price | 0 credits per\_token before discounts |
| Typical time | about 10.0 s |

## Request

**Required:** `text`\
**Optional:** `voice_name`

```json theme={null}
{
  "model": "gemini-3.1-flash-tts-preview",
  "text": "[softly] [worried] Hamara shaadi ka video... ab kya hoga.",
  "voice_name": "Zephyr"
}
```

| Field | Allowed | Default |
| - | - | - |
| `voice_name` | `Zephyr`, `Charon`, `Kore`, `Fenrir`, `Aoede`, `Puck` | `"Zephyr"` |

Reference inputs take asset ids from [`POST /v1/uploads`](/uploads) or an earlier output's `asset_id`.
Prices and allowed values come from the live catalog; `GET /v1/models/gemini-3.1-flash-tts-preview` is always current.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.