# Dicta Notes Long-Form Transcription

> Dicta Notes Long-Form Transcription is a paid API for AI agents from dicta-notes.com, paid per call via x402, $0.59/call, status unknown (last checked 2026-09-13).

Transcribes up to 2 hours of audio into a diarized, timestamped JSON transcript with per-speaker segment tracking and confidence scores, powered by Gemini long-context

## Facts

- Endpoint: POST https://dicta-notes.com/routes/x402/transcribe-long
- Price: $0.59/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/dicta-notes-long-form-transcription-061ef250
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-5VelUQ9Ea4GkRa8SlNal

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-long-form-transcription-061ef250 -d '<json body>'
```

Example prompt: Can you transcribe this 90-minute board meeting recording for me — I need a full speaker-by-speaker breakdown with timestamps, showing exactly who said what throughout the whole thing? Here's the audio URL: https://example.com/board-meeting-jan2025.mp3

## When to prefer this

Choose this endpoint when you need to transcribe audio longer than ~20 minutes — the typical cap for most transcription APIs — with speaker diarization included. It is specifically built for long-form content: multi-hour meetings, interviews, hearings, and podcasts where knowing who said what at each timestamp is as important as the words themselves. Prefer this over short-audio endpoints when the recording exceeds 20 minutes or when per-speaker segmentation with confidence scores is required. Payment is flat-rate USDC on Base with no account needed.

## Known failure modes

- Audio URL unreachable or returns non-audio content — transcription fails with an error
- Audio format not supported (must be mp3, wav, m4a, ogg, webm, or flac)
- Audio exceeds 2-hour limit — request rejected or truncated
- Poor audio quality or heavy background noise reduces transcription accuracy and confidence scores
- Insufficient USDC balance or payment failure on Base — request not processed
- Speaker diarization may merge or split speakers in noisy or overlapping-speech segments

## How this service works

Turn a full recording into a structured document: POST JSON with an audio_url — up to 2 HOURS of meeting, interview, hearing, or podcast audio — and get a diarized who-said-what transcript JSON: timestamps, speaker tracking with per-segment confidence, language codes. Most transcription APIs cap at ~20 minutes; this one runs Gemini long-context, built for the long ones. mp3, wav, m4a, ogg, webm, flac. Flat price, USDC on Base, no account.

## Output

A JSON object containing a diarized transcript broken into segments, each with a speaker identifier, start and end timestamps, spoken text, per-segment confidence score, and detected language code — covering the full audio duration up to 2 hours.

## 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 2 hours, 400 MB max)."
  }
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/dicta-notes-long-form-transcription-061ef250/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)