# Speech-to-Text Transcription (Whisper Large v3 Turbo)

> Speech-to-Text Transcription (Whisper Large v3 Turbo) is a paid API for AI agents from flat-rate-llm.kikoribera03.workers.dev, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-14).

Transcribes audio files to text using Whisper large v3 turbo, returning the transcript, detected language, duration, and timed segments with optional word-level timestamps.

## Facts

- Endpoint: POST https://flat-rate-llm.kikoribera03.workers.dev/v1/ai/transcribe
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/speech-to-text-transcription-whisper-large-v3-turbo-93729a38
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_IgoTGfGyTHrVjkXD-h_L9

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-whisper-large-v3-turbo-93729a38 -d '<json body>'
```

Example prompt: Can you transcribe this audio recording for me — here's the URL: https://example.com/meeting.mp3 — and include word-level timestamps so I can see exactly when each word was spoken?

## When to prefer this

Choose this endpoint when you need fast, affordable audio transcription without account setup or API keys, supporting ~100 languages with timed segment output and optional word-level timestamps. Ideal for agents that need to process one audio file at a time via URL or base64, at $0.01 per call with no subscription overhead. Prefer over self-hosted Whisper when you want zero infrastructure, or over larger providers when cost and simplicity matter.

## Known failure modes

- Audio file URL not accessible or returns non-200 status — transcription fails with an error
- File exceeds 10 MB limit — request rejected
- Unsupported audio format provided — returns format error
- Network timeout fetching remote audio URL — transcription fails
- Very low audio quality or silence — returns empty or inaccurate transcript
- Language detection confidence may be low for very short or noisy clips

## How this service works

Transcribes an audio file with Whisper large v3 turbo: pass an https URL (mp3, wav, flac, m4a, ogg, up to 10 MB) or base64 audio in a POST. Returns the text, the detected language with its probability, the duration, and timed segments; add words=true for word-level timestamps. Around 100 languages. You are only charged if the transcript is delivered. No API key, no account.

## Output

Returns a JSON object containing the full transcript text, the detected language code (e.g. 'en', 'es') with a confidence probability, the total audio duration in seconds, an array of timed segments each with start/end times and segment text, and optionally word-level timestamps for each word when words=true is requested.

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/speech-to-text-transcription-whisper-large-v3-turbo-93729a38/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from flat-rate-llm.kikoribera03.workers.dev](https://www.zero.xyz/host/flat-rate-llm.kikoribera03.workers.dev/llms.txt)