# Speech to Text Transcriber (/docs/experiments/speech-to-text-transcriber)



Upload an audio file and receive a transcript using **Workers AI Whisper** (`@cf/openai/whisper-large-v3-turbo`). Validates file size and content type before calling the model.

## Features [#features]

* **POST /transcribe** - Multipart upload with field `audio`
* **Whisper model** - `@cf/openai/whisper-large-v3-turbo`
* **Validation** - Max 2 MB, `audio/*` types only
* **Timing** - Returns `durationMs` for the transcription call

## API Reference [#api-reference]

### POST /transcribe [#post-transcribe]

Transcribe an uploaded audio file.

**`audio`** `file` (required, multipart)

Audio file (max 2 MB). Accepted types include `audio/mpeg`, `audio/wav`, `audio/webm`, `audio/ogg`, and other `audio/*` MIME types.

#### Example Request [#example-request]

```bash
curl -X POST "https://your-worker.workers.dev/transcribe" \
  -F "audio=@sample.mp3"
```

#### Success Response [#success-response]

```json
{
  "text": "Hello, this is a test recording.",
  "language": "en",
  "durationMs": 842
}
```

#### Error Codes [#error-codes]

* `400` - Missing or invalid audio (`INVALID_AUDIO`)
* `502` - Transcription failed or empty result (`TRANSCRIBE_ERROR`)

## Use Cases [#use-cases]

* Add speech-to-text to edge apps without external API keys
* Prototype voice note or meeting transcription workflows
* Learn Workers AI audio model integration patterns

## Limitations [#limitations]

* Max upload size 2 MB per request (Whisper model limits apply)
* No chunking for long recordings; split large files client-side
* Requires Workers AI enabled on your Cloudflare account

## Deployment [#deployment]

<Steps>
  <Step>
    ### Click the deploy button [#click-the-deploy-button]

    [![Deploy to Cloudflare Workers](https://deploy.workers.cloudflare.com/button)](https://deploy.workers.cloudflare.com/?url=https://github.com/shrinathsnayak/cloudflare-experiments/tree/main/apps/experiments/speech-to-text-transcriber)
  </Step>

  <Step>
    ### Deploy [#deploy]

    Enable Workers AI. The `AI` binding is declared in `wrangler.json`.
  </Step>

  <Step>
    ### Test your deployment [#test-your-deployment]

    ```bash
    curl -X POST "https://your-worker.workers.dev/transcribe" -F "audio=@sample.mp3"
    ```
  </Step>
</Steps>

## Local Development [#local-development]

```bash
cd apps/experiments/speech-to-text-transcriber
npm install
npm run dev
```

## Configuration [#configuration]

| Binding | Purpose                  |
| ------- | ------------------------ |
| `AI`    | Workers AI Whisper model |

## Cloudflare Features Used [#cloudflare-features-used]

* **[Workers](https://developers.cloudflare.com/workers/)** - Edge compute runtime
* **[Workers AI](https://developers.cloudflare.com/workers-ai/)** - Whisper speech-to-text