Name: Suno Bark API: Expressive Text to Speech and Audio
Brand: magicapi
SKU: api-magicapi-text-prompted-audio-generator-suno-ai-bark
Availability: InStock
Author: API Market

Shashank Agarwal

# 🔊 Text-to-Audio Generator API (Suno Bark)

## Overview
Bark is Suno's text-prompted generative audio model. It turns a text `prompt` into audio and follows cues in the text such as `[laughs]` and hesitations like "uh".

Pick a preset voice in `history_prompt` (an `announcer` voice or speakers 0 to 9 in 13 languages) or pass your own `.npz` history file in `custom_history_prompt`. `text_temp` and `waveform_temp` control how varied the result is. Set `output_full` to `true` to also get the full generation as an `.npz` file that you can reuse as a history prompt.

## Features
- **Expressive speech**: cues such as `[laughs]` and filler words in the prompt shape the delivery.
- **131 preset voices**: `announcer` plus `<language>_speaker_0` to `<language>_speaker_9` for 13 languages (de, en, es, fr, hi, it, ja, ko, pl, pt, ru, tr, zh).
- **Custom history prompts**: pass your own `.npz` file in `custom_history_prompt`; it overrides `history_prompt`.
- **Reusable generations**: `output_full` returns the full generation as an `.npz` file in `prompt_npz`, for use as a later history prompt.
- **Variation control**: `text_temp` and `waveform_temp` (default 0.7; 1.0 more diverse, 0.0 more conservative).

## Use Cases
1. **Expressive voice lines**: dialogue with laughter and hesitation for games, animation and podcasts.
2. **Multilingual speech**: preset speakers in 13 languages.
3. **Consistent characters**: reuse an `.npz` history file to keep the same voice across clips.
4. **Audio prototyping**: quick spoken drafts of scripts and ads.

## Visual Examples
### Example Input
A short self-introduction with a hesitation and a `[laughs]` cue, all other fields at their defaults:

```json
{
  "prompt": "Hello, my name is Suno. And, uh \u2014 and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."
}
```

### Example Output
[Listen to the example output](https://blog.api.market/wp-content/uploads/2026/10/bark-output-xmrr36kc-api-market.mp3)

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `prompt` | string | No | `"Hello, my name is Suno. And, uh \u2014 and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."` |  | Input prompt |
| `history_prompt` | string | No | none | `announcer`, or `<lang>_speaker_0` to `<lang>_speaker_9` where `<lang>` is one of `de`, `en`, `es`, `fr`, `hi`, `it`, `ja`, `ko`, `pl`, `pt`, `ru`, `tr`, `zh` (131 values) | Preset voice (history choice) for audio cloning, chosen from the list |
| `custom_history_prompt` | string (URL) | No | none |  | URL of your own .npz history file for audio cloning. Overrides history_prompt. |
| `text_temp` | number | No | `0.7` |  | Text generation temperature (1.0 more diverse, 0.0 more conservative) |
| `waveform_temp` | number | No | `0.7` |  | Waveform generation temperature (1.0 more diverse, 0.0 more conservative) |
| `output_full` | boolean | No | `false` |  | Return the full generation as a .npz file to be used as a history prompt |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.11 per API unit.
- **1 API unit = 1 request with up to 440 seconds of processing time.** A request that runs longer uses one unit per started 440-second block.
- Typical prompts like the example finish well within one unit, so a request costs $0.11.
- **Example cost**: the example request took 45.4 seconds of processing = 1 unit = **$0.11**.
- **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/text-prompted-audio-generator-suno-ai-bark`

### 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 2 seconds and an overall timeout of 900 seconds (15 minutes) work well. The example took about 45 seconds of processing; requests can wait longer before they start.

### Endpoints

#### Create a Prediction
```bash
curl -X POST "https://prod.api.market/api/v1/magicapi/text-prompted-audio-generator-suno-ai-bark/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787",
    "input": {
      "prompt": "Hello, my name is Suno. And, uh \u2014 and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."
    }
  }'
```

Response (201 Created):
```json
{
  "id": "xmrr36kcz5rg80d1c6nscjjq94",
  "version": "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787",
  "status": "starting",
  "created_at": "2026-10-22T03:33:07.216Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/text-prompted-audio-generator-suno-ai-bark/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "xmrr36kcz5rg80d1c6nscjjq94",
  "status": "succeeded",
  "output": {
    "audio_out": "https://blog.api.market/wp-content/uploads/2026/10/bark-output-xmrr36kc-api-market.mp3",
    "prompt_npz": null
  },
  "error": null,
  "created_at": "2026-10-22T03:33:07.216Z",
  "started_at": "2026-10-22T03:38:33.362Z",
  "completed_at": "2026-10-22T03:39:18.776Z"
}
```

`output` is an object: `audio_out` is the URL of the generated audio, and `prompt_npz` is the URL of the `.npz` history file when `output_full` is `true` (otherwise `null`).

### 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 `history_prompt` that is not in the list or a `custom_history_prompt` that is not a URL.
- **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/text-prompted-audio-generator-suno-ai-bark";

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: "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787", 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 = 900000;
  const pollInterval = 2000;
  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 15 minutes");
}

createAndWaitForPrediction({
    "prompt": "Hello, my name is Suno. And, uh \u2014 and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."
  }).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/text-prompted-audio-generator-suno-ai-bark"


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": "b76242b40d67c76ab6742e987628a2a9ac019e11d56ab96c4e91ce03b79b2787", "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 = 900
    poll_interval = 2
    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 15 minutes")


print(create_and_wait_for_prediction({
    "prompt": "Hello, my name is Suno. And, uh \u2014 and I like pizza. [laughs] But I also have other interests such as playing tic tac toe."
}))
```

## FAQ
- **How do I choose a voice?**
  - Set `history_prompt` to a preset such as `en_speaker_6` or `announcer`, or pass your own `.npz` file in `custom_history_prompt`.
- **Can I keep the same voice across requests?**
  - Yes. Set `output_full` to `true`, save the `prompt_npz` file from the output, and send it as `custom_history_prompt` in later requests.
- **How do I add laughter or hesitation?**
  - Write it into the prompt, for example `[laughs]` or "uh", as in the example.
- **How much does a request cost?**
  - $0.11 per request covering up to 440 seconds of processing. The example took 45 seconds.
- **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 or need assistance, you can reach out to us through the embedded chat on the bottom right corner of the page or send an email to hello@magicapi.com.


Suno Bark API: generate expressive speech with laughs and pauses from text, with 131 preset voices in 13 languages, plus music and sound cues.