# Delx Audio Transcription

> Delx Audio Transcription is a paid API for AI agents from api.delx.ai, paid per call via x402, $0.02/call, status unknown (last checked 2026-09-15).

Transcribes a single WAV audio clip (up to 60 seconds, 2 MiB) to text for $0.02 USDC per call, returning the transcript and a SHA-256 receipt with no API key or audio retention.

## Facts

- Endpoint: POST https://api.delx.ai/api/v1/x402/transcribe-audio
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-audio-transcription-c69bd144
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_8iy7Np1SeyPqCxC5RwSXU

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 delx-audio-transcription-c69bd144 -d '<json body>'
```

Example prompt: Can you transcribe this voice note for me? I'll give you the WAV file as base64 — it's about 30 seconds long and I need the text of what was said.

## When to prefer this

Choose this endpoint when you need a quick, pay-per-use transcription of a short WAV clip (under 60 seconds) without setting up an API key or subscription. It is ideal for one-off voice notes, support call snippets, or meeting excerpts where you need a verifiable SHA-256 receipt and audio privacy (no retained audio). Prefer alternatives for longer audio, non-WAV formats, bulk batch transcription, or when you need speaker diarization or timestamps.

## Known failure modes

- Audio exceeds 2 MiB decoded size — request rejected
- Audio clip longer than 60 seconds — request rejected
- Invalid or malformed base64 encoding — decoding error returned
- Non-WAV audio format submitted — format rejection error
- Payment of $0.02 USDC not completed — 402 Payment Required response
- URL or file path submitted instead of base64 data — rejected per schema

## How this service works

Delx is an independent AI agent lab building and studying continuity, recovery, verifiable work and governed exchange for autonomous systems.

## Output

Returns the full text transcript of the spoken audio, along with a SHA-256 hash receipt that serves as a verifiable record of the transcription. No audio is retained after processing.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audio_base64": {
   "type": "string",
   "maxLength": 2800000,
   "minLength": 1,
   "description": "One base64-encoded WAV up to 2 MiB decoded and 60 seconds. audio/wav data-URI prefixes are accepted. URLs, file paths, and model/version fields are rejected."
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "text": "hello agents",
  "bytes": 12,
  "model": "vaibhavs10/incredibly-fast-whisper",
  "sha256": "2d6c7c2b3f3c8e1e7b0d3a5b6e7f8a9b1234567890abcdef1234567890abcdef",
  "provider": "replicate",
  "text_url": "https://api.delx.ai/api/v1/generated-transcripts/9c2e1b84f0a14d2e9c8b7a6543210fed.txt",
  "media_type": "text/plain",
  "input_sha256": "34a8815e9c57e321194d50f2ea8b64394019fb8038c9aefd7a9a306a5030fc31",
  "generation_id": "9c2e1b84f0a14d2e9c8b7a6543210fed",
  "sale_price_usdc": 0.02,
  "gross_margin_usd": 0.0164,
  "upstream_cost_usd": 0.0036,
  "provider_prediction_id": "tr-example-prediction"
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/delx-audio-transcription-c69bd144/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from api.delx.ai](https://www.zero.xyz/host/api.delx.ai/llms.txt)