# Dicta Notes Short Audio Transcription

> Dicta Notes Short Audio Transcription is a paid API for AI agents from dicta-notes.com, paid per call via x402, $0.1/call, status unknown (last checked 2026-10-13).

Transcribes audio files up to 15 minutes into speaker-labeled, timestamped, multilingual transcript segments using Gemini AI

## Facts

- Endpoint: POST https://dicta-notes.com/routes/x402/transcribe?utm_source=zero.xyz
- Price: $0.1/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dicta-notes-short-audio-transcription-5d83bcae
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_hv5xw0xrXtnE1Yk0k_3V6

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 dicta-notes-short-audio-transcription-5d83bcae -d '<json body>'
```

Example prompt: Can you transcribe this voicemail recording for me — here's the URL: https://example.com/voicemail.mp3 — and tell me who said what with timestamps?

## When to prefer this

Choose this endpoint when you need fast, speaker-labeled, timestamped transcription of audio files up to 15 minutes without requiring an account or API key. It is ideal for voicemails, short call recordings, voice memos, and podcast clips in any spoken language. For recordings over 15 minutes (up to 2 hours), use the sibling /transcribe-long endpoint instead.

## Known failure modes

- Audio URL not publicly accessible — returns error if file requires authentication or is behind a firewall
- File exceeds 15 minutes or 100 MB limit — should use the long-form /transcribe-long endpoint instead
- Unsupported audio format — only mp3, wav, m4a, ogg, webm, flac are supported
- Payment failure — USDC transaction on Base not confirmed
- Audio too noisy or low quality — transcript may have gaps or low confidence scores
- URL is malformed or audio file is corrupted — returns processing error

## How this service works

Transcribe short audio fast: POST JSON with an audio_url (voicemail, call recording, voice memo, podcast clip — up to 15 min) and get Gemini-powered transcript JSON back with speaker-labeled, timestamped segments — any spoken language, auto-detected and labeled per segment. Handles mp3, wav, m4a, ogg, webm, flac. $0.10 flat in USDC on Base — no account, no API key. For hour-long meetings use /routes/x402/transcribe-long.

## Output

Returns a JSON object with a full transcript string, an array of segments each containing speaker label, text, start_time, end_time, language, and optional confidence score; plus a speakers array, total duration_seconds, primary language, and all languages_detected in the audio.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "store": {
   "type": "boolean",
   "description": "Optional. When true, encrypt and store the transcript JSON for 60 days."
  },
  "audio_url": {
   "type": "string",
   "format": "uri",
   "description": "Public http(s) URL of the audio file (up to 15 minutes, 100 MB max)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dicta-notes-short-audio-transcription-5d83bcae/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from dicta-notes.com](https://www.zero.xyz/host/dicta-notes.com/llms.txt)