Name: Boson AI Higgs Audio v2 Text-to-Speech API
Brand: magicapi
SKU: api-magicapi-expressive-text-to-speech-api-lucataco-higgs-audio-v2
Availability: InStock
Author: API Market

Shashank Agarwal

# 🔊 Text-to-Speech API (Boson AI Higgs Audio v2)

## Overview
Higgs Audio v2 is a text-to-speech audio foundation model from Boson AI. Its developer describes it as excelling in expressive audio generation.

Send the `text` to speak. Optionally describe the recording setting in `scene_description`, add a `system_message`, and tune sampling with `temperature`, `top_p` and `top_k`. Each request returns the URL of one WAV audio file.

## Features
- **Text to speech**: `text` is spoken in one audio file.
- **Scene description**: `scene_description` gives the audio context (default "Audio is recorded from a quiet room.").
- **Sampling controls**: `temperature` (0.1 to 1, default 0.3), `top_p` (0.1 to 1, default 0.95) and `top_k` (1 to 100, default 50).
- **Length limit**: `max_new_tokens` (256 to 2048, default 1024) caps the number of audio tokens generated.
- **System message**: an optional custom `system_message`.
- **WAV output**: the result is a WAV file URL.

## Use Cases
1. **Narration**: read out articles, lessons or product descriptions.
2. **Voice prompts**: spoken messages for apps, kiosks and phone menus.
3. **Video voice-overs**: generate the spoken track for short videos.
4. **Accessibility**: offer an audio version of written content.

## Visual Examples
### Example Input
Text: "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years", with the default scene description, `temperature` 0.3 and `max_new_tokens` 1024.

```json
{
  "text": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years",
  "top_k": 50,
  "top_p": 0.95,
  "temperature": 0.3,
  "max_new_tokens": 1024,
  "system_message": "",
  "scene_description": "Audio is recorded from a quiet room."
}
```

### Example Output
[Listen to the example output](https://blog.api.market/wp-content/uploads/2026/11/higgs-audio-v2-output-d6f8jksj-api-market.wav)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `text` | string | No | `The sun rises in the east and sets in the west` |  | Text to convert to speech |
| `temperature` | number | No | `0.3` | 0.1 to 1 | Controls randomness in generation. Lower values are more deterministic. |
| `top_p` | number | No | `0.95` | 0.1 to 1 | Nucleus sampling parameter. Controls diversity of generated audio. |
| `top_k` | integer | No | `50` | 1 to 100 | Top-k sampling parameter. Limits vocabulary to top k tokens. |
| `max_new_tokens` | integer | No | `1024` | 256 to 2048 | Maximum number of audio tokens to generate |
| `scene_description` | string | No | `Audio is recorded from a quiet room.` |  | Scene description for audio context |
| `system_message` | string | No | `""` |  | Custom system message (optional) |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.0033 per API unit.
- **1 API unit = 1 request with up to 3 seconds of processing.** A request that takes longer is billed one more unit for each started 3-second block (for example, 10 seconds of processing is 4 units, $0.0132).
- **Example cost**: the example request took 4.8 seconds of processing, which is 2 units ($0.0066).
- Longer texts take longer to generate and use more units.
- **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/expressive-text-to-speech-api-lucataco-higgs-audio-v2`

### 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/expressive-text-to-speech-api-lucataco-higgs-audio-v2/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "f5945a3453e6258b3a82b10bfefdfd171fa756c8e42a7c5e07326f3a98ef8e09",
    "input": {
      "text": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years",
      "top_k": 50,
      "top_p": 0.95,
      "temperature": 0.3,
      "max_new_tokens": 1024,
      "system_message": "",
      "scene_description": "Audio is recorded from a quiet room."
    }
  }'
```

Response (201 Created):
```json
{
  "id": "d6f8jksjmxrmr0d1mvmr7zkvd8",
  "version": "f5945a3453e6258b3a82b10bfefdfd171fa756c8e42a7c5e07326f3a98ef8e09",
  "status": "starting",
  "created_at": "2026-11-04T14:14:23.143Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/expressive-text-to-speech-api-lucataco-higgs-audio-v2/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "d6f8jksjmxrmr0d1mvmr7zkvd8",
  "status": "succeeded",
  "output": "https://blog.api.market/wp-content/uploads/2026/11/higgs-audio-v2-output-d6f8jksj-api-market.wav",
  "error": null,
  "created_at": "2026-11-04T14:14:23.143Z",
  "started_at": "2026-11-04T14:14:56.960Z",
  "completed_at": "2026-11-04T14:15:01.805Z"
}
```

`output` is a single URL string pointing to the generated WAV 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 `temperature` outside 0.1 to 1 or a `max_new_tokens` outside 256 to 2048.
- **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
Requests are rate limited to keep usage fair. If you receive a 429 response, wait and retry with exponential backoff.

## 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/expressive-text-to-speech-api-lucataco-higgs-audio-v2";

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: "f5945a3453e6258b3a82b10bfefdfd171fa756c8e42a7c5e07326f3a98ef8e09", 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": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years",
  "top_k": 50,
  "top_p": 0.95,
  "temperature": 0.3,
  "max_new_tokens": 1024,
  "system_message": "",
  "scene_description": "Audio is recorded from a quiet room."
}).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/expressive-text-to-speech-api-lucataco-higgs-audio-v2"


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": "f5945a3453e6258b3a82b10bfefdfd171fa756c8e42a7c5e07326f3a98ef8e09", "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": "The sun rises in the east and sets in the west. This simple fact has been observed by humans for thousands of years",
    "top_k": 50,
    "top_p": 0.95,
    "temperature": 0.3,
    "max_new_tokens": 1024,
    "system_message": "",
    "scene_description": "Audio is recorded from a quiet room."
}))
```

## FAQ
- **Is `text` required?**
  - No. If you leave it out the model speaks its default text, "The sun rises in the east and sets in the west". Send your own `text` in practice.
- **Can I choose a voice?**
  - There is no voice field. Use `scene_description` and `system_message` to give context for the audio.
- **How long can the audio be?**
  - `max_new_tokens` (256 to 2048, default 1024) caps the number of audio tokens generated. Raise it if long texts are cut off.
- **How much does a request cost?**
  - $0.0033 for each started 3 seconds of processing. The example took 4.8 seconds and cost 2 units ($0.0066).
- **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.


Convert text to speech with Higgs Audio v2: send text and an optional scene description, get a WAV file back. $0.0033 per request, pay as you go.