Speaker labels: transcribe audio with who said what (diarization)
Transcribe a meeting, interview, call or podcast with speaker labels: each turn says which speaker talked, with start and end times (Deepgram Nova-3). MP3/WAV up to 15 minutes, other formats up to 2 MB, by URL or upload. Optional redaction of personal data (pii), card numbers (pci) or numbers, and subtitles with the speaker in each line. Use for meeting minutes, interview transcripts, call reviews and podcast show notes.
Inputs
| Name | Type | Description |
|---|---|---|
url (required) | string | Absolute http(s) URL of the recording (MP3/WAV up to 15 minutes; M4A, OGG, WebM or FLAC up to 2 MB); or POST the file itself (raw body, multipart `file` part, or base64 in JSON) |
language | string | Spoken language code such as en, es, de or fr (default: detected) |
redact | string | pii (names, addresses, phone numbers and other personal data), pci (card numbers) or numbers: replaced in the transcript |
subtitles | string | srt or vtt: also return subtitles, each line starting with its speaker |
Request
Over HTTP, with a card key from /credits:
curl -H "Authorization: Bearer adt_…" "https://glyphcall.com/transcribe/speakers?url=https%3A%2F%2Fupload.wikimedia.org%2Fwikipedia%2Fcommons%2F7%2F77%2FTofino_pronunciation.mp3"
Without a key, the same URL answers 402 Payment Required with x402 and MPP terms, so an agent with a wallet pays per call in USDC (Base, Polygon, Arbitrum or Solana over x402; Base or Tempo over MPP) and retries.
Example result
{
"url": "https://upload.wikimedia.org/wikipedia/commons/7/77/Tofino_pronunciation.mp3",
"durationSeconds": 0.9,
"speakers": 1,
"turns": [
{
"speaker": 1,
"start": 0.08,
"end": 0.88,
"text": "Tofino."
}
],
"text": "Tofino.",
"language": "en",
"wordCount": 1,
"model": "@cf/deepgram/nova-3"
}
From an AI agent (MCP)
Add the MCP server to Claude, Cursor or any MCP client. This tool is transcribe_speakers, and the first 25 successful calls are free:
https://glyphcall.com/mcp