# Agent Tools UK — Audio/Video Transcription (Whisper)

> Agent Tools UK — Audio/Video Transcription (Whisper) is a paid API for AI agents from agent-tools-production-e6aa.up.railway.app, paid per call via x402, $0.03/call, status unknown (last checked 2026-10-15).

Transcribes speech from an audio or video file (up to 15 minutes) using Whisper, returning full text, detected language, duration, and timestamped segments.

## Facts

- Endpoint: POST https://agent-tools-production-e6aa.up.railway.app/v1/transcribe?utm_source=zero.xyz
- Price: $0.03/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agent-tools-uk-audio-video-transcription-whisper-906a94bf
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_ao9ml4HSYUixrzzzviotW

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 agent-tools-uk-audio-video-transcription-whisper-906a94bf -d '<json body>'
```

Example prompt: Can you transcribe this voice note for me? Here's the URL: https://example.com/meeting-recording.mp3 — I need the full text and timestamps for each segment.

## When to prefer this

Choose this endpoint when you need accurate speech-to-text with automatic language detection and timestamped segment output from common audio/video formats (mp3, m4a, wav, ogg, mp4, webm) up to 15 minutes. Prefer it over generic STT services when you need both full text and per-segment timestamps in a single call, and when you want Whisper-quality multilingual transcription without managing your own Whisper infrastructure.

## Known failure modes

- 413 error if the audio or video file exceeds 15 minutes in length
- 422 error if the file is not a recognised audio or video format
- File fetch failure if the provided URL is not publicly accessible
- Base64 decode error if the encoded content is malformed or too large (>20 MB)
- Low accuracy if audio quality is very poor or contains heavy background noise

## How this service works

Transcribe speech from an audio or video file (mp3, m4a, wav, ogg, mp4, webm) up to 15 minutes, using Whisper. Language is detected automatically. Use when you need the words from a voice note, meeting, podcast clip or video. Send {url} or {base64}, optional language (2-letter code). Returns {language, duration, text, segments with start/end times}. Errors: 413 over 15 minutes, 422 not audio.

## Output

Returns a JSON object containing: the detected language code, total audio duration in seconds, full transcript text as a single string, and an array of segments each with start time, end time, and the spoken text for that segment.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "url": {
   "type": "string",
   "description": "Public URL of the file. Provide url OR base64."
  },
  "base64": {
   "type": "string",
   "description": "File contents, base64-encoded (max 20 MB). Provide url OR base64."
  },
  "language": {
   "type": "string",
   "description": "Optional 2-letter language code, e.g. en"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agent-tools-uk-audio-video-transcription-whisper-906a94bf/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agent-tools-production-e6aa.up.railway.app](https://www.zero.xyz/host/agent-tools-production-e6aa.up.railway.app/llms.txt)