# Gemini 3.1 Flash TTS (Preview) API — pricing & specs

Gemini 3.1 Flash TTS (Preview) is a text-to-speech model from Google DeepMind. On KeepRouter, Gemini 3.1 Flash TTS (Preview) costs $1.00 per 1M input tokens and $0.000500 per second of audio, billed pay-as-you-go with no monthly fee; the cost follows measured input tokens and the length of the audio returned. Call it through a compatible KeepRouter endpoint supported by its active route, with the model id `gemini-3.1-flash-tts-preview`.

| Spec | Value |
|---|---|
| Maker | Google DeepMind |
| Modality | Text-to-speech |
| Input price | $1.00 per 1M tokens |
| Output price | $0.000500 per second of audio |
| Capabilities | Text-to-speech |
| Endpoint | POST /v1/audio/speech |
| Model id | `gemini-3.1-flash-tts-preview` |

## Call it via audio speech endpoint

Send text-to-speech requests to POST /v1/audio/speech.

### cURL

```bash
curl https://keeprouter.com/v1/audio/speech \
  -H "Authorization: Bearer $KEEPROUTER_KEY" -H "Content-Type: application/json" \
  -d '{"model":"gemini-3.1-flash-tts-preview","input":"Hello from KeepRouter","voice":"alloy"}' --output speech.mp3
```

### Python

```python
import os
from openai import OpenAI
client = OpenAI(base_url="https://keeprouter.com/v1", api_key=os.environ["KEEPROUTER_KEY"])
audio = client.audio.speech.create(model="gemini-3.1-flash-tts-preview", input="Hello from KeepRouter", voice="alloy")
```

### JavaScript

```js
const res = await fetch("https://keeprouter.com/v1/audio/speech", {
  method: "POST",
  headers: { Authorization: "Bearer " + process.env.KEEPROUTER_KEY, "Content-Type": "application/json" },
  body: JSON.stringify({ model: "gemini-3.1-flash-tts-preview", input: "Hello from KeepRouter", voice: "alloy" }),
});
```

## Estimate API costs

At the current KeepRouter customer price, an example workload of 1,000 input tokens and 6 seconds of generated audio per request costs approximately $0.004000 per request. At 100 requests per day, that is $12.00 over 30 days. This is a usage estimate, excluding processing fees, taxes, retries and application infrastructure. Actual usage, cache hits and supported generation durations need their own checks.

[Adjust quantities in the API cost calculator](/tools/api-cost-calculator?model=gemini-3.1-flash-tts-preview).

## How to evaluate Gemini 3.1 Flash TTS (Preview)

Gemini 3.1 Flash TTS (Preview) is listed on KeepRouter as text-to-speech under the exact id `gemini-3.1-flash-tts-preview`. Use /v1/audio/speech for the listed route; a maker's upstream features do not automatically apply to this gateway endpoint. No context limit is asserted here because the exact upstream limit has not been verified for this catalog entry.

**First workload:** Synthesize a representative script and measure returned audio duration, intelligibility, startup delay and cost per generated second.

**Before production:** Output billing is duration-based; do not interpret the published output rate as a per-million-token price.

## Public model usage evidence

No public, exact-variant usage figure has been verified for this KeepRouter model id. Missing data is not zero usage; family-level or maker-wide traffic is not presented as this model's traffic.

## Published examples and cases

No exact-model customer case has been verified for this entry. The workload above is an evaluation recipe, not a claim of a public deployment.

## Source and verification boundary

[Official Google DeepMind website](https://deepmind.google/). KeepRouter's live catalog is authoritative for the customer price and enabled endpoint shown here; the maker remains authoritative for upstream model capabilities and limits.

## Pricing and implementation guides

- [Calculate your API workload cost](https://keeprouter.com/tools/api-cost-calculator)
- [KeepRouter API keys: move from free to paid models](https://keeprouter.com/blog/keeprouter-api-key-free-to-paid)

## Related models

- [Gemini 3.1 Pro (Preview)](https://keeprouter.com/models/gemini-3.1-pro-preview.md) by Google DeepMind — $4.00 per 1M input tokens and $18.00 per 1M output tokens
- [Gemini 3.1 Flash-Lite](https://keeprouter.com/models/gemini-3.1-flash-lite.md) by Google DeepMind — $0.5000 per 1M input tokens and $1.50 per 1M output tokens
- [Gemini 3.1 Pro Custom Tools (Preview)](https://keeprouter.com/models/gemini-3.1-pro-preview-customtools.md) by Google DeepMind — $4.00 per 1M input tokens and $18.00 per 1M output tokens
- [Gemini 3 Flash (Preview)](https://keeprouter.com/models/gemini-3-flash-preview.md) by Google DeepMind — $1.00 per 1M input tokens and $3.00 per 1M output tokens
- [Gemini 3.5 Flash](https://keeprouter.com/models/gemini-3.5-flash.md) by Google DeepMind — $1.50 per 1M input tokens and $9.00 per 1M output tokens
- [Veo 3.1 Lite (1080p)](https://keeprouter.com/models/veo-3.1-lite-1080p.md) by Google DeepMind — $0.0800 per second of video

## More

- [All models & pricing](https://keeprouter.com/models.md)
- [Quickstart](https://keeprouter.com/docs/quickstart.md)
- [Get an API key](https://keeprouter.com/login?returnTo=%2Fconsole%2Fkeys%3Fmodel%3Dgemini-3.1-flash-tts-preview)

_Catalog facts and prices last changed 2026-10-03._
_Page content reviewed 2026-09-28._