Name: Gemini 3.1 Flash TTS API: Expressive Text to Speech
Brand: magicapi
SKU: api-magicapi-fast-expressive-text-to-speech-google-gemini-3-1-flash-tts
Availability: InStock
Author: API Market

Shashank Agarwal

# 🗣️ Text-to-Speech API (Google Gemini 3.1 Flash TTS)

## Overview
Gemini 3.1 Flash TTS is Google's text-to-speech model. Its developer describes it as fast and expressive, with 30 voices and support for more than 70 languages.

Send the `text` to speak, pick a `voice` and a `language_code`, and optionally describe the delivery in `prompt` (tone, pace, accent, emotion). Tags such as `[sigh]`, `[laughing]`, `[whispering]`, `[shouting]` or `[extremely fast]` inside the text change how individual passages are spoken. Each request returns the URL of one audio file.

## Features
- **Style prompt**: describe the delivery in plain language with `prompt`, for example "Say this in a calm, professional tone" or "Speak with excitement and energy". The default is `Say the following.`
- **Inline delivery tags**: put markup such as `[sigh]`, `[laughing]`, `[whispering]`, `[shouting]` or `[extremely fast]` in `text` to change single passages.
- **30 voices**: `Kore` (default), `Puck`, `Charon`, `Zephyr`, `Algenib` and 25 more, all listed in the parameter table.
- **87 language codes**: from `af-ZA` to `vi-VN`, with `en-US` as the default.
- **Long inputs**: up to 4,000 bytes of `text` and 4,000 bytes of `prompt` per request.

## Use Cases
1. **Voiceovers**: narration for product videos, tutorials and explainers in a chosen tone.
2. **Character voices**: game and story dialogue with acted delivery, as in the example below.
3. **Multilingual audio**: the same script spoken in many languages by setting `language_code`.
4. **App and phone prompts**: short spoken messages for apps, assistants and phone menus.

## Visual Examples
### Example Input
Text with an inline style tag, the `Algenib` voice and US English:

```json
{
  "text": "[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?",
  "voice": "Algenib",
  "prompt": "Say the following.",
  "language_code": "en-US"
}
```

### Example Output
[Listen to the example output](https://blog.api.market/wp-content/uploads/2026/10/gemini-3-1-flash-tts-output-gfc9y5v6-api-market.wav)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | Yes | none |  | The text to convert to speech. Supports markup tags like [sigh], [laughing], [whispering], [shouting], [extremely fast] for expressive delivery. Maximum 4,000 bytes. |
| `voice` | string | No | `Kore` | `Achernar`, `Achird`, `Algenib`, `Algieba`, `Alnilam`, `Aoede`, `Autonoe`, `Callirrhoe`, `Charon`, `Despina`, `Enceladus`, `Erinome`, `Fenrir`, `Gacrux`, `Iapetus`, `Kore`, `Laomedeia`, `Leda`, `Orus`, `Pulcherrima`, `Puck`, `Rasalgethi`, `Sadachbia`, `Sadaltager`, `Schedar`, `Sulafat`, `Umbriel`, `Vindemiatrix`, `Zephyr`, `Zubenelgenubi` | Voice to use for speech generation |
| `prompt` | string | No | `Say the following.` |  | Style instructions that control how the text is spoken. Describe the tone, pace, accent and emotion in natural language, for example "Say this in a calm, professional tone" or "Speak with excitement and energy". Maximum 4,000 bytes. |
| `language_code` | string | No | `en-US` | `af-ZA`, `am-ET`, `ar-001`, `ar-EG`, `az-AZ`, `be-BY`, `bg-BG`, `bn-BD`, `ca-ES`, `ceb-PH`, `cmn-CN`, `cmn-tw`, `cs-CZ`, `da-DK`, `de-DE`, `el-GR`, `en-AU`, `en-GB`, `en-IN`, `en-US`, `es-419`, `es-ES`, `es-MX`, `et-EE`, `eu-ES`, `fa-IR`, `fi-FI`, `fil-PH`, `fr-CA`, `fr-FR`, `gl-ES`, `gu-IN`, `he-IL`, `hi-IN`, `hr-HR`, `ht-HT`, `hu-HU`, `hy-AM`, `id-ID`, `is-IS`, `it-IT`, `ja-JP`, `jv-JV`, `ka-GE`, `kn-IN`, `ko-KR`, `kok-IN`, `la-VA`, `lb-LU`, `lo-LA`, `lt-LT`, `lv-LV`, `mai-IN`, `mg-MG`, `mk-MK`, `ml-IN`, `mn-MN`, `mr-IN`, `ms-MY`, `my-MM`, `nb-NO`, `ne-NP`, `nl-NL`, `nn-NO`, `or-IN`, `pa-IN`, `pl-PL`, `ps-AF`, `pt-BR`, `pt-PT`, `ro-RO`, `ru-RU`, `sd-IN`, `si-LK`, `sk-SK`, `sl-SI`, `sq-AL`, `sr-RS`, `sv-SE`, `sw-KE`, `ta-IN`, `te-IN`, `th-TH`, `tr-TR`, `uk-UA`, `ur-PK`, `vi-VN` | Language for the speech output |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.005 per API unit.
- **1 API unit = 100 weighted tokens; an output token counts 1, an input token counts 0.05.**
- That is **$2.50 per million input tokens** and **$50 per million output tokens**.
- Output tokens are the generated audio, so the cost grows with the length of the speech. Each request is rounded up to a whole unit.
- **Example cost**: the example request used 39 input tokens and 279 output tokens: 39 x 0.05 + 279 = 280.95 weighted tokens, rounded up to 3 units = **$0.015**.
- **Failed or cancelled predictions are not billed.**
- **GET requests to check prediction status** are free and don't count toward API unit usage.
- **No monthly subscription fee.**

## API Documentation

### Base URL
All API requests go to: `https://prod.api.market/api/v1/magicapi/fast-expressive-text-to-speech-google-gemini-3-1-flash-tts`

### Authentication
Send your api.market API key in the `x-api-market-key` header:
```
x-api-market-key: YOUR_API_MARKET_KEY
```

### Asynchronous Processing
**IMPORTANT**: This API is asynchronous. The flow is:
1. Send a POST request to `/predictions`. A successful request returns **201 Created** with a prediction `id` and a `status` of `starting` or `processing`.
2. Poll GET `/predictions/{id}` with that ID.
3. Keep polling while `status` is `starting` or `processing`.
4. Stop when `status` is `succeeded` (read `output`), `failed` or `canceled` (read `error`).

A polling interval of 1 second and an overall timeout of 600 seconds (10 minutes) work well.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/fast-expressive-text-to-speech-google-gemini-3-1-flash-tts/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "google/gemini-3.1-flash-tts",
    "input": {
      "text": "[like dracula] Hey there, I'\''m a new text to speech model and I can say things in many different ways. How can I help you today?",
      "voice": "Algenib",
      "prompt": "Say the following.",
      "language_code": "en-US"
    }
  }'
```

Response (201 Created):
```json
{
  "id": "gfc9y5v64hrmw0d1c6sbhcxar0",
  "version": "google/gemini-3.1-flash-tts",
  "status": "starting",
  "created_at": "2026-10-22T03:40:44.110Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/fast-expressive-text-to-speech-google-gemini-3-1-flash-tts/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "gfc9y5v64hrmw0d1c6sbhcxar0",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/10/gemini-3-1-flash-tts-output-gfc9y5v6-api-market.wav",
  "error": null,
  "created_at": "2026-10-22T03:40:44.110Z",
  "started_at": "2026-10-22T03:40:44.310Z",
  "completed_at": "2026-10-22T03:40:50.330Z"
}
```

`output` is a single URL string pointing to the generated audio file.

### Status Codes
- **201 Created**: prediction created (POST `/predictions`). This is the normal success response.
- **200 OK**: prediction details returned (GET `/predictions/{id}`).
- **400 Bad Request**: invalid input, for example a missing `text` or a `voice` that is not in the list.
- **401 Unauthorized**: missing or invalid API key.
- **404 Not Found**: no prediction with that ID.
- **429 Too Many Requests**: rate limit exceeded.
- **500 Internal Server Error** or **503 Service Unavailable**: temporary server problem; retry later.

## Rate Limits
All plans allow 10 requests per second. Requests above that return `429 Too Many Requests`; back off before retrying and honour any `Retry-After` header. Polling a prediction with GET is free but still counts toward the per-second limit, so poll every 1 to 5 seconds rather than in a tight loop.

## Error Handling
- Check the HTTP status code of every request and read the response body for the error message.
- A prediction can also end with `status` set to `failed`; the `error` field then explains why. Failed predictions are not billed.
- Retry 429, 500 and 503 responses with exponential backoff. Fix the input before retrying a 400.

## Implementation Guide
### Example Code

#### JavaScript
```javascript
const apiKey = "YOUR_API_MARKET_KEY";
const baseUrl = "https://prod.api.market/api/v1/magicapi/fast-expressive-text-to-speech-google-gemini-3-1-flash-tts";

async function createAndWaitForPrediction(input) {
  const response = await fetch(`${baseUrl}/predictions`, {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "x-api-market-key": apiKey
    },
    body: JSON.stringify({ version: "google/gemini-3.1-flash-tts", input })
  });

  if (response.status !== 201) {
    throw new Error(`API error: ${response.status} ${await response.text()}`);
  }

  const prediction = await response.json();
  return pollForResults(prediction.id);
}

const delay = (ms) => new Promise((resolve) => setTimeout(resolve, ms));

async function pollForResults(predictionId) {
  const maxTimeout = 600000;
  const pollInterval = 1000;
  const startTime = Date.now();

  while (Date.now() - startTime < maxTimeout) {
    const response = await fetch(`${baseUrl}/predictions/${predictionId}`, {
      headers: { "x-api-market-key": apiKey }
    });

    if (!response.ok) {
      throw new Error(`API error: ${response.status} ${await response.text()}`);
    }

    const prediction = await response.json();

    if (prediction.status === "succeeded") {
      return prediction.output;
    }

    if (prediction.status === "failed" || prediction.status === "canceled") {
      throw new Error(`Prediction ${prediction.status}: ${prediction.error || "Unknown error"}`);
    }

    await delay(pollInterval);
  }

  throw new Error("Prediction timed out after 10 minutes");
}

createAndWaitForPrediction({
    "text": "[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?",
    "voice": "Algenib",
    "prompt": "Say the following.",
    "language_code": "en-US"
  }).then((output) => console.log(output));
```

#### Python
```python
import time
import requests

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/fast-expressive-text-to-speech-google-gemini-3-1-flash-tts"


def create_and_wait_for_prediction(input_data):
    headers = {"Content-Type": "application/json", "x-api-market-key": API_KEY}
    response = requests.post(
        f"{BASE_URL}/predictions",
        headers=headers,
        json={"version": "google/gemini-3.1-flash-tts", "input": input_data},
    )

    if response.status_code != 201:
        raise Exception(f"API error: {response.status_code} {response.text}")

    return poll_for_results(response.json()["id"])


def poll_for_results(prediction_id):
    max_timeout = 600
    poll_interval = 1
    headers = {"x-api-market-key": API_KEY}
    start_time = time.time()

    while time.time() - start_time < max_timeout:
        response = requests.get(f"{BASE_URL}/predictions/{prediction_id}", headers=headers)

        if response.status_code != 200:
            raise Exception(f"API error: {response.status_code} {response.text}")

        prediction = response.json()

        if prediction["status"] == "succeeded":
            return prediction["output"]

        if prediction["status"] in ("failed", "canceled"):
            raise Exception(f"Prediction {prediction['status']}: {prediction.get('error') or 'Unknown error'}")

        time.sleep(poll_interval)

    raise Exception("Prediction timed out after 10 minutes")


print(create_and_wait_for_prediction({
    "text": "[like dracula] Hey there, I'm a new text to speech model and I can say things in many different ways. How can I help you today?",
    "voice": "Algenib",
    "prompt": "Say the following.",
    "language_code": "en-US"
}))
```

## FAQ
- **How do I control the tone and style?**
  - Describe it in `prompt` (for example "Speak with excitement and energy") and add tags such as `[whispering]` or `[laughing]` inside `text` for individual passages.
- **Which voices and languages can I use?**
  - 30 voices (default `Kore`) and 87 language codes (default `en-US`). Both lists are in the parameter table.
- **How long can the text be?**
  - Up to 4,000 bytes of `text` and 4,000 bytes of `prompt` per request. Split longer scripts into several requests.
- **How much does a request cost?**
  - It depends on the tokens used: $2.50 per million input tokens and $50 per million output tokens, rounded up to a whole unit of $0.005. The example request cost $0.015.
- **Is the 201 response from POST an error?**
  - No. 201 Created means the prediction was accepted. Use the returned `id` to poll GET `/predictions/{id}` until `status` is `succeeded`, `failed` or `canceled`.
- **What if my prediction fails?**
  - Failed predictions are not billed. Read the `error` field, adjust the input and try again.

## Contact Us
If you have any questions, reach out to us through the chat on the bottom right of the page. You can also email our support team at hello@magicapi.com.


Convert text to expressive speech with Google Gemini 3.1 Flash TTS: 30 voices, 87 language codes, style prompts and inline tags like [whispering].