# Combify Compute Speech-to-Text Transcription

> Combify Compute Speech-to-Text Transcription is a paid API for AI agents from compute.combify.app, paid per call via x402, $0.015/call, status unknown (last checked 2026-10-10).

Transcribes audio files (voice notes, meeting clips, podcasts) to text using Whisper large-v3-turbo for $0.015 USDC per call

## Facts

- Endpoint: POST https://compute.combify.app/transcribe?utm_source=zero.xyz
- Price: $0.015/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-10
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/combify-compute-speech-to-text-transcription-e7a56aa7
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_2ECVOTukTmWQPbcAQyn42

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 combify-compute-speech-to-text-transcription-e7a56aa7 -d '<json body>'
```

Example prompt: Can you transcribe this voice note for me? I'll send it as a base64-encoded audio file — it's an English meeting recording about 3 minutes long.

## When to prefer this

Choose this endpoint when your input is audio (voice notes, meeting recordings, podcasts, interviews) and you need a text transcript. Use /chat instead if the input is already text. Priced at $0.015 USDC per call via x402, making it cost-effective for individual clips. Backed by Whisper large-v3-turbo for high accuracy across 100+ languages.

## Known failure modes

- 402 Payment Required — call was made without valid x402 payment
- Audio exceeds 8 MB decoded size limit — request rejected
- Unsupported audio format or corrupted base64 encoding — transcription fails
- Ambiguous or incorrectly specified language hint leading to reduced accuracy
- Network timeout for large audio files near the size limit

## How this service works

Speech to text for voice notes, meeting clips, and podcasts: send audio, get a transcript (Whisper large-v3-turbo), fixed price $0.015 USDC. Use this when the input is audio; use /chat when the input is already text. POST JSON body {audio (required, base64, max 8 MB decoded), language (optional hint)}. Returns {text, duration_s}. Unpaid calls get 402; paid calls settle only on success.

## Output

Returns a JSON object with 'text' (the full transcript as a string) and 'duration_s' (the length of the audio in seconds). Unpaid calls receive a 402 Payment Required response; successful payment settles only on successful transcription.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audio": {
   "type": "string",
   "description": "Base64-encoded audio, max 8 MB decoded"
  },
  "language": {
   "type": "string",
   "description": "Optional language hint"
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/combify-compute-speech-to-text-transcription-e7a56aa7/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from compute.combify.app](https://www.zero.xyz/host/compute.combify.app/llms.txt)