# Audio Transcription via Whisper Large v3 Turbo (Cloudflare Workers AI)

> Audio Transcription via Whisper Large v3 Turbo (Cloudflare Workers AI) is a paid API for AI agents from ai-policy-kit.moneymaker-ai.workers.dev, paid per call via x402, $0.005/call, status unknown (last checked 2026-10-28).

Transcribes audio files to text using OpenAI Whisper Large v3 Turbo running on Cloudflare Workers AI, returning transcript, language, word count, and duration.

## Facts

- Endpoint: GET https://ai-policy-kit.moneymaker-ai.workers.dev/api/ai/transcribe?utm_source=zero.xyz
- Price: $0.005/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-28
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/audio-transcription-via-whisper-large-v3-turbo-cloudflare-workers-ai-13b9b452
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_mFalG8x8Tq8dYSS0mmhlX

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability audio-transcription-via-whisper-large-v3-turbo-cloudflare-workers-ai-13b9b452
```

Example prompt: Can you transcribe the audio at https://example.com/interview.mp3 for me? I think it's in English — give me the full transcript with word count.

## When to prefer this

Choose this endpoint when you need fast, low-cost speech-to-text transcription for short audio clips (under 1 MB) via a public URL or base64, especially when you want Whisper Large v3 Turbo quality without managing your own infrastructure. Ideal for agents that need to process voice memos, short podcast clips, or interview snippets on demand. Not suited for long audio files or real-time streaming transcription.

## Known failure modes

- Audio URL is not publicly accessible or returns a non-200 response
- Audio file exceeds 1 MB size limit
- Unsupported audio format
- Invalid base64 encoding if using audio_base64
- Language code is invalid or unsupported ISO format
- Network timeout fetching remote audio URL
- Transcription accuracy issues for heavy accents or noisy audio

## How this service works

Generate an AI_POLICY.md and a pull request template with an AI-disclosure section for your open-source repo. Free, runs in your browser.

## Output

Returns a JSON object containing the full transcript text, detected language code, word count, audio duration in seconds, the engine used (Whisper Large v3 Turbo on Cloudflare Workers AI), estimated neurons used, and a note that audio is not stored. Example output includes fields: text, language, word_count, duration_seconds, engine, neurons_estimated, note.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "$schema": "https://json-schema.org/draft/2020-12/schema",
 "required": [
  "input"
 ],
 "properties": {
  "input": {
   "type": "object",
   "required": [
    "type",
    "method"
   ],
   "properties": {
    "type": {
     "type": "string",
     "const": "http"
    },
    "method": {
     "enum": [
      "GET"
     ],
     "type": "string"
    },
    "queryParams": {
     "type": "object",
     "required": [],
     "properties": {
      "language": {
       "type": "string",
       "description": "optional ISO code, e.g. en"
      },
      "segments": {
       "enum": [
        "true",
        "false"
       ],
       "type": "string"
      },
      "audio_url": {
       "type": "string",
       "description": "public https URL of the audio (max 1 MB)"
      },
      "audio_base64": {
       "type": "string",
       "description": "or base64 audio (POST)"
      }
     }
    }
   },
   "additionalProperties": false
  },
  "output": {
   "type": "object",
   "required": [
    "type"
   ],
   "properties": {
    "type": {
     "type": "string"
    },
    "example": {
     "type": "object"
    }
   }
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "note": "Machine transcription; may contain errors. Audio is not stored.",
  "text": "they are hard, because that goal will serve to organize and measure the best of our energies and skills, because that challenge is one that we're willing to accept, one we are unwilling to postpone, and one we intend to win, and the others too.",
  "engine": "@cf/openai/whisper-large-v3-turbo on Cloudflare Workers AI",
  "language": "en",
  "word_count": 45,
  "duration_seconds": 20,
  "neurons_estimated": 15.55
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/audio-transcription-via-whisper-large-v3-turbo-cloudflare-workers-ai-13b9b452/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from ai-policy-kit.moneymaker-ai.workers.dev](https://www.zero.xyz/host/ai-policy-kit.moneymaker-ai.workers.dev/llms.txt)