Transcribe audio: speech to text with Whisper

$0.01 per call · failed calls are never charged · no account needed: a card key or USDC

Transcribe audio to text: send an audio file URL (or POST the file) and get the transcript, detected language, duration and word count from Whisper large-v3-turbo; subtitles=srt or vtt adds subtitles, timestamps=true adds timed segments and words. MP3, WAV, M4A and OGG up to 5 MB, 90+ languages. Use for voice notes, meeting and podcast clips, call recordings and subtitles.

Buy credits by card (from $1) Example result (JSON)

Inputs

NameTypeDescription
url (required)stringAbsolute http(s) URL of an audio file (max 5 MB); or POST the file itself (raw body, multipart `file` part, or base64 in JSON)
subtitlesstringsrt or vtt: also return subtitle text
timestampsstringtrue: also return timed segments and words
languagestringSpoken language code such as en, sv or de (default: detected)

Request

Over HTTP, with a card key from /credits:

curl -H "Authorization: Bearer adt_…" "https://api.glyphcall.com/audio/transcribe?url=https%3A%2F%2Fcommons.wikimedia.org%2Fwiki%2FSpecial%3AFilePath%2FEn-us-hello.ogg"

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://commons.wikimedia.org/wiki/Special:FilePath/En-us-hello.ogg",
  "text": "Hello!",
  "language": "en",
  "durationSeconds": 0.487625,
  "wordCount": 1,
  "model": "@cf/openai/whisper-large-v3-turbo"
}

From an AI agent (MCP)

Add the MCP server to Claude, Cursor or any MCP client. This tool is audio_transcribe, and the first 25 successful calls are free:

https://api.glyphcall.com/mcp

Related tools