# Delx Commerce Audio Transcription API

> Delx Commerce Audio Transcription API is a paid API for AI agents from commerce.delx.ai, paid per call via x402, $0.02/call, status unknown (last checked 2026-10-02).

Transcribes a base64-encoded WAV audio clip (up to 2 MiB / 60 seconds) to text using Whisper, paid per-call in USDC via x402 with no signup required.

## Facts

- Endpoint: POST https://commerce.delx.ai/api/v1/x402/transcribe-audio?utm_source=zero.xyz
- Price: $0.02/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-02
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/delx-commerce-audio-transcription-api-97f955b4
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_DksTwKcLiC-Bl5Sn4uVOq

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-commerce-audio-transcription-api-97f955b4 -d '<json body>'
```

Example prompt: Can you transcribe this WAV audio clip for me? Here's the base64-encoded audio data: [base64 string]. Just give me the text of what was said.

## When to prefer this

Choose this endpoint when you need a fast, pay-per-use speech-to-text transcription for short WAV clips (under 60 seconds) without any account setup, subscription, or API key management. It is particularly well-suited for AI agent workflows that need verifiable, auditable transcription results with cryptographic delivery proofs and USDC micropayment settlement on Base or Solana.

## Known failure modes

- Audio exceeds 2 MiB decoded or 60 seconds — rejected with validation error
- Non-WAV audio format submitted — rejected, only audio/wav accepted
- URL or file path submitted instead of base64 data — explicitly rejected
- Base64 string malformed or empty — validation error
- Payment not provided or insufficient USDC — x402 payment required response
- Audio contains no intelligible speech — may return empty or near-empty text

## How this service works

Pay-per-result APIs for agents. No signup. Exact price. Verifiable delivery. USDC on Base + Solana via x402.

## Output

Returns a JSON object containing the full transcribed text string, a hosted URL to the plain-text transcript, a SHA256 hash of the output for verification, the input SHA256, a generation ID, byte count, the model name used (vaibhavs10/incredibly-fast-whisper via Replicate), the sale price in USDC, and upstream cost details.

## 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-commerce-audio-transcription-api-97f955b4/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from commerce.delx.ai](https://www.zero.xyz/host/commerce.delx.ai/llms.txt)