# Gemini 3.1 | Flash | Text to Speech

Gemini 3.1 Flash TTS generates expressive AI speech from text with audio tags that control pacing, tone, pauses, and emphasis on eachlabs.

## API Information

- **Model Slug:** gemini-3-1-flash-text-to-speech
- **Branded URL:** https://www.eachlabs.ai/google/google-tts/gemini-3-1-flash-text-to-speech
- **Provider:** Google
- **Category:** Text to Voice
- **Output Type:** audio
- **Status:** active
- **Version:** 0.0.1
- **Base Cost:** Gemini 3.1 Flash TTS: $1.00 / 1M text input tokens + $20.00 / 1M audio output tokens
- **Estimated Processing Time:** 5 seconds
- **Last Updated:** 2026-07-06
- **Interactive Demo:** https://www.eachlabs.ai/ai-models/gemini-3-1-flash-text-to-speech

## Pricing

- **Charge Type:** dynamic
- **Pricing Details:** Gemini 3.1 Flash TTS: $1.00 / 1M text input tokens + $20.00 / 1M audio output tokens

### Pricing Rules

| Condition | Pricing |
| --- | --- |
| Rule 1 | Gemini 3.1 Flash TTS: $1.00 / 1M text input tokens + $20.00 / 1M audio output tokens |
| Default (fallback) | $0.00000000 |

## Input Schema

No input parameters documented.

## Example Request

```bash
curl -X POST https://api.eachlabs.ai/v1/prediction/ \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "gemini-3-1-flash-text-to-speech",
  "input": {}
}'
```

## Output Schema

Response returned by `GET /v1/prediction/{id}` when the job completes:

```json
{
  "status": "success",
  "predictionID": "string",
  "output": "string (URL of generated audio)",
  "metrics": {
    "predict_time": "number (seconds)"
  }
}
```

## Polling

```bash
curl https://api.eachlabs.ai/v1/prediction/{PREDICTION_ID} \
  -H "Authorization: Bearer YOUR_API_KEY"
```

| Status | Meaning |
|--------|---------|
| `processing` | Still running — poll again |
| `success` | Done — read `output` |
| `error` | Failed — read `message` / `details` |

## Webhook (alternative to polling)

Pass `"webhook_url": "https://your.host/path"` in the create request. Eachlabs POSTs this payload when the job ends:

```json
{
  "exec_id": "prediction-uuid",
  "status": "succeeded",
  "output": "https://...",
  "error": ""
}
```

`status` is `"succeeded"` or `"failed"`. `exec_id` equals the `predictionID` from create. Return 2xx within 30 seconds.

## Errors

Error body: `{ "status": "error", "message": "...", "details": "..." }`

| Code | Meaning |
|------|---------|
| `400` | Invalid input |
| `401` | Missing / invalid `Authorization` bearer token |
| `404` | Unknown model or prediction id |
| `429` | Rate limit — 100 creates / min, 10 concurrent per key |
| `5xx` | Retry with backoff |

## Overview

**Gemini 3.1 | Flash | Text to Speech Overview**

The **Gemini 3.1 | Flash | Text to Speech** model from Google transforms written text into natural-sounding spoken audio, solving the need for quick, high-quality voice synthesis in applications like content creation and accessibility tools. Part of Google's **google-tts** family, this model leverages the efficient Gemini 3.1 Flash architecture to deliver fast text-to-voice conversion with low latency, making it ideal for real-time uses. Its primary differentiator is the integration of advanced multimodal capabilities from the Gemini series, enabling context-aware speech generation that adapts tone and style based on input prompts. Available through the **Gemini 3.1 | Flash | Text to Speech API** on platforms like each::labs, it supports developers and creators in building immersive audio experiences without heavy computational demands. Whether for podcasts, virtual assistants, or e-learning, this Google text-to-voice solution prioritizes speed and naturalness.

## Usage Notes

- API Base URL: `https://api.eachlabs.ai/v1`
- Authentication: send `Authorization: Bearer YOUR_API_KEY`. Generate a key from the Eachlabs dashboard at https://www.eachlabs.ai/dashboard/api-keys.
- File-typed parameters (`*_url`, `image_url`, `video_url`, `audio_url`, etc.) accept publicly-reachable HTTPS URLs only. Upload your asset first (GCS / S3 / your CDN) and pass the resulting URL. Data-URIs and localhost URLs are rejected.
- For structured parameters (arrays / objects) send real JSON values, not stringified payloads.
- Monetary values are reported in USD; per-token / per-megapixel rates may be billed in micro-cents internally.
- Prefer `webhook_url` over polling for long-running predictions — see the Webhook Callback section.