# WithZero Audio Transcription via GPT-4o (ZeroClick)

> WithZero Audio Transcription via GPT-4o (ZeroClick) is a paid API for AI agents from agents.withzero.xyz, paid per call via MPP or x402, $0.3/call, status unknown (last checked 2026-09-15).

Transcribes base64-encoded audio (WAV or MP3, up to 15 MB) to text using OpenAI's GPT-4o transcription model, billed per call via ZeroClick's x402 payment layer.

## Facts

- Endpoint: POST https://agents.withzero.xyz/api/v1/audio/transcripts/gpt-4o-transcribe
- Price: $0.3/call
- Payment: MPP, x402
- Status: unknown
- Last checked: 2026-09-15
- Activations on Zero: 3
- Tags: x402
- Canonical page: https://www.zero.xyz/c/withzero-audio-transcription-via-gpt-4o-zeroclick-df233551
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_FLUo1AdXhmataOr4pVHWs

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 withzero-audio-transcription-via-gpt-4o-zeroclick-df233551 -d '<json body>'
```

Example prompt: Can you transcribe this MP3 audio clip for me? I'll give you the base64-encoded audio data — it's a short voice memo I recorded earlier and I need the text of what was said.

## When to prefer this

Choose this endpoint when you need GPT-4o-quality speech-to-text transcription without managing your own OpenAI API key or billing, and when you are operating in an agent context that supports x402 autonomous micropayments. Especially suitable for agents needing pay-per-use transcription of WAV or MP3 audio up to 15 MB with no vendor account setup.

## Known failure modes

- Audio exceeds 15 MB decoded size — request rejected
- Unsupported format provided (not wav or mp3) — validation error
- Invalid or malformed base64 string — decoding failure
- Audio quality too poor for accurate transcription — degraded or incomplete output
- Insufficient USDC balance or payment failure via x402 — payment error preventing execution

## How this service works

Create media, research companies and people, publish to the web, remember context, deploy apps, and schedule work—on demand, without vendor accounts or API keys. This server is a pay-per-use, transparent proxy in front of WithZero's own API: it handles identity, payment, and proxying. Agents can purchase autonomously or with their human's approval. This document is the source of truth for agents: it lists the complete verified paid surface with each operation's live price in its x-payment-info. Endpoints not listed here are not part of the supported catalog. The live catalog at /manifest.json is authoritative for prices and any free included units (prices[].includedUnits) - some meters include free usage per account before any charge.

## Output

A text transcript of the spoken content in the submitted audio. The response contains the transcribed text produced by GPT-4o from the decoded audio data.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audio": {
   "type": "string",
   "maxLength": 20971524,
   "minLength": 1,
   "description": "Base64-encoded audio to transcribe (decoded size up to 15 MB)."
  },
  "format": {
   "enum": [
    "wav",
    "mp3"
   ],
   "type": "string",
   "description": "Container format of the audio."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/withzero-audio-transcription-via-gpt-4o-zeroclick-df233551/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agents.withzero.xyz](https://www.zero.xyz/host/agents.withzero.xyz/llms.txt)