Name: WhisperX API: Fast Audio Transcription with Timestamps
Brand: magicapi
SKU: api-magicapi-accelerated-audio-transcription-daanelson-whisperx
Availability: InStock
Author: API Market

Shashank Agarwal

# 🎙️ Audio Transcription API (daanelson WhisperX)

## Overview
This API transcribes speech in an audio file with WhisperX, a batched and accelerated version of Whisper speech recognition.

Send an `audio` URL. By default the API returns a list of transcript segments, each with `start` and `end` times in seconds and the `text` spoken in that range. Set `only_text` to `true` to get the text without segment metadata, or `align_output` to `true` for word-level timing (English only).

## Features
- **Timed segments**: each segment has `start`, `end` (seconds) and `text`.
- **Word-level timing**: `align_output` adds word timings. Its developer notes this only works for English for now.
- **Text only**: `only_text` returns the transcript text without segment metadata.
- **Batched transcription**: `batch_size` (default 32) sets how many pieces of the audio are transcribed in parallel.

## Use Cases
1. **Subtitles**: turn segment start and end times into caption files for videos.
2. **Meeting and interview notes**: transcribe recordings into searchable text.
3. **Podcast transcripts**: publish a text version of each episode.
4. **Voice data processing**: convert spoken audio into text for search, tagging or analysis.

## Visual Examples
### Example Input
[Listen to the example input](https://blog.api.market/wp-content/uploads/2026/10/whisperx-input-api-market.wav): a 49-second English recording of short read sentences.

Settings: `batch_size` 32. All other fields were left at their defaults (`align_output` `false`, `only_text` `false`).

### Example Output
```json
[
  {
    "end": 30.772,
    "start": 2.557,
    "text": " The little tales they tell are false. The door was barred, locked and bolted as well. Ripe pears are fit for a queen's table. A big wet stain was on the round carpet. The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon. The room was crowded with a mild wob."
  },
  {
    "end": 48.558,
    "start": 32.999,
    "text": " The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid. The beetle droned in the hot June sun."
  }
]
```

## Input Parameters
| Field | Type | Required | Default | Allowed values | Description |
| --- | --- | --- | --- | --- | --- |
| `audio` | string (URL) | Yes |  |  | Audio file URL |
| `batch_size` | integer | No | `32` |  | Parallelization of input audio transcription |
| `align_output` | boolean | No | `false` |  | Return word-level timing in addition to the batched transcription. Only works for English for now |
| `only_text` | boolean | No | `false` |  | Return only the text; otherwise segment metadata is returned as well |
| `debug` | boolean | No | `false` |  | Print out memory usage information |

## Pricing
- **Pay As You Go (PAYG) pricing**: you only pay for what you use.
- **Price**: $0.039 per API unit.
- **1 API unit = 1 successful request with up to 156 seconds of processing.** A request that runs longer is billed one more unit for each started 156-second block (for example, 200 seconds of processing is 2 units, $0.078). Longer audio files take longer to process.
- The example request above (49 seconds of audio) took 3.9 seconds of processing, which is 1 unit, so it cost $0.039.
- **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/accelerated-audio-transcription-daanelson-whisperx`

### 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/accelerated-audio-transcription-daanelson-whisperx/predictions" \
  -H "Content-Type: application/json" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY" \
  -d '{
    "version": "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd",
    "input": {
      "audio": "https://blog.api.market/wp-content/uploads/2026/10/whisperx-input-api-market.wav",
      "batch_size": 32
    }
  }'
```

Response (201 Created):
```json
{
  "id": "g2wn8sh2thrga0d1d8evcc7fer",
  "version": "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd",
  "status": "starting",
  "created_at": "2026-10-23T18:54:16.963Z"
}
```

#### Check Prediction Status
```bash
curl -X GET "https://prod.api.market/api/v1/magicapi/accelerated-audio-transcription-daanelson-whisperx/predictions/{id}" \
  -H "x-api-market-key: YOUR_API_MARKET_KEY"
```

Response when the prediction has finished (200 OK):
```json
{
  "id": "g2wn8sh2thrga0d1d8evcc7fer",
  "status": "succeeded",
  "output": [
    {
      "end": 30.772,
      "start": 2.557,
      "text": " The little tales they tell are false. The door was barred, locked and bolted as well. Ripe pears are fit for a queen's table. A big wet stain was on the round carpet. The kite dipped and swayed but stayed aloft. The pleasant hours fly by much too soon. The room was crowded with a mild wob."
    },
    {
      "end": 48.558,
      "start": 32.999,
      "text": " The room was crowded with a wild mob. This strong arm shall shield your honour. She blushed when he gave her a white orchid. The beetle droned in the hot June sun."
    }
  ],
  "error": null,
  "created_at": "2026-10-23T18:54:16.963Z",
  "started_at": "2026-10-23T18:54:17.963Z",
  "completed_at": "2026-10-23T18:54:29.963Z"
}
```

With the default settings `output` is an array of segments, each an object with `start` and `end` (seconds) and `text`. With `only_text` set to `true` it holds the transcript text without segment metadata.

### 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 `audio`.
- **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/accelerated-audio-transcription-daanelson-whisperx";

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: "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd", 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({
  "audio": "https://blog.api.market/wp-content/uploads/2026/10/whisperx-input-api-market.wav",
  "batch_size": 32
}).then((segments) => {
  for (const segment of segments) {
    console.log(`[${segment.start} - ${segment.end}]${segment.text}`);
  }
});
```

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

API_KEY = "YOUR_API_MARKET_KEY"
BASE_URL = "https://prod.api.market/api/v1/magicapi/accelerated-audio-transcription-daanelson-whisperx"


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": "9aa6ecadd30610b81119fc1b6807302fd18ca6cbb39b3216f430dcf23618cedd", "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")


segments = create_and_wait_for_prediction({
    "audio": "https://blog.api.market/wp-content/uploads/2026/10/whisperx-input-api-market.wav",
    "batch_size": 32
})
for segment in segments:
    print(f"[{segment['start']} - {segment['end']}]{segment['text']}")
```

## FAQ
- **What does the output contain?**
  - By default, a list of segments with `start` and `end` in seconds and the `text` spoken in between. Set `only_text` to `true` to get the text without the timing metadata.
- **Can I get word-level timestamps?**
  - Set `align_output` to `true`. Its developer notes this only works for English for now.
- **Why do segment texts start with a space?**
  - That is how the model returns them. Trim each `text` if you join or display segments.
- **How is a request billed?**
  - By processing time: $0.039 covers up to 156 seconds of processing, and each further started 156-second block adds one unit.
- **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, check that the audio URL is reachable 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.


Transcribe speech from an audio URL into segments with start and end times using WhisperX. $0.039 per request up to 156 seconds of processing, pay as you go.