# Speech-to-Text Transcription via Whisper (Cloudflare Workers AI)

> Speech-to-Text Transcription via Whisper (Cloudflare Workers AI) is a paid API for AI agents from api.fadeandco.workers.dev, paid per call via x402, $0.004/call, status unknown (last checked 2026-10-30).

Transcribes an audio file (public HTTPS URL or base64, up to 6 MB; WAV, MP3, M4A, OGG) to text using a Cloudflare Workers AI Whisper model, returning the transcript and optional timestamped segments.

## Facts

- Endpoint: POST https://api.fadeandco.workers.dev/api/agent-intel/speech-to-text-transcribe-turbo?utm_source=zero.xyz
- Price: $0.004/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-30
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/speech-to-text-transcription-via-whisper-cloudflare-workers-ai-5dbaad42
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_aaLcHdZVaJqj3zWgiuJkV

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 speech-to-text-transcription-via-whisper-cloudflare-workers-ai-5dbaad42 -d '<json body>'
```

Example prompt: Can you transcribe this audio file for me? Here's the URL: https://example.com/meeting-recording.mp3 — I need the full text and any timestamps if available.

## When to prefer this

Choose this endpoint when you need fast, affordable speech-to-text transcription from a public audio URL or base64-encoded audio in WAV, MP3, M4A, or OGG format (under 6 MB), and want optional timestamped segments. Ideal for agents automating transcription of voice memos, meeting recordings, podcast clips, or interview audio at $0.004 per call. Prefer alternatives if you need real-time streaming transcription, speaker diarization, or files larger than 6 MB.

## Known failure modes

- Audio file exceeds 6 MB limit — request rejected
- Unsupported audio format (e.g., FLAC, AAC) — model may fail or return error
- Inaccessible or non-public audio URL — fetch failure
- Malformed base64 input — decoding error
- No speech detected in audio — empty or minimal transcript returned
- Network timeout fetching large audio files
- Whisper model binding unavailable — server-side configuration error

## How this service works

Transcribes an audio file (a public https URL or base64, up to 6 MB; WAV, MP3, M4A or OGG as the model accepts them) to text with a Cloudflare Workers AI Whisper model, returning the text and any timestamped segments the model gives. Requires the env.AI binding.

## Output

Returns the full transcribed text of the audio file along with any timestamped segment data provided by the Whisper model (e.g., start/end times and text per segment). Response quality depends on audio clarity and length (up to 6 MB).

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audioUrl": {
   "type": "string",
   "description": "Public https URL of the audio file (WAV, MP3, M4A or OGG), up to 6 MB"
  },
  "audioBase64": {
   "type": "string",
   "description": "Or the audio itself: base64 data (no data: prefix), up to 6 MB decoded"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/speech-to-text-transcription-via-whisper-cloudflare-workers-ai-5dbaad42/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.fadeandco.workers.dev](https://www.zero.xyz/host/api.fadeandco.workers.dev/llms.txt)