OrbTop

AI Audio to Text Transcriber

AIDEVELOPER TOOLSAUTOMATION
Try on Apify

AI Audio to Text Transcriber

Transcribe audio files to text using OpenAI Whisper. Supply a list of public audio file URLs and your OpenAI API key — the actor downloads each file, sends it to the Whisper API, and returns a verbatim transcript alongside language detection, duration, and timed segments.

What it does

  • Accepts a list of public audio file URLs (MP3, MP4, M4A, WAV, WEBM, OGG, FLAC)
  • Downloads each file to temporary storage (max 25 MB per file — OpenAI limit)
  • Transcribes via OpenAI Whisper (whisper-1) with verbose_json output
  • Returns the full text transcript, detected language, audio duration, and segment-level timestamps
  • Processes up to 3 files concurrently for faster batch runs
  • Saves one dataset record per file, including error records for files that fail

Use cases

  • Podcast indexing and search
  • Meeting recording notes
  • Compliance and call-center transcription
  • Generating training data for NLP models
  • Subtitles and captions for video content
  • Multilingual content analysis

Input

Field Type Required Description
audioUrls Array Yes Public audio file URLs to transcribe
openaiApiKey String Yes Your OpenAI API key (sk-...). Not stored.
language String No ISO 639-1 hint (e.g. en, es, ja). Omit for auto-detect.
maxItems Integer No Maximum files to transcribe per run. Default: 15.

Supported audio formats: MP3, MP4, M4A, WAV, WEBM, OGG, FLAC Max file size: 25 MB (OpenAI Whisper hard limit)

Example input

{
  "audioUrls": [
    "https://example.com/podcast-episode-1.mp3",
    "https://example.com/meeting-recording.wav"
  ],
  "openaiApiKey": "sk-...",
  "language": "en",
  "maxItems": 10
}

Output

One dataset record per audio file.

Field Type Description
sourceUrl String Original audio file URL
transcript String Full verbatim transcription text
language String Detected language (e.g. english, spanish)
durationSeconds Number Audio duration in seconds
segments String JSON array of timed segments [{start, end, text}]
model String Whisper model used (whisper-1)
transcribedAt String ISO timestamp
status String success or error
errorMsg String Error description on failure, null on success

Example output record

{
  "sourceUrl": "https://example.com/podcast-ep1.mp3",
  "transcript": "Welcome to today's episode. Today we're discussing the future of AI...",
  "language": "english",
  "durationSeconds": 1823.4,
  "segments": "[{\"start\":0.0,\"end\":3.2,\"text\":\"Welcome to today's episode.\"}]",
  "model": "whisper-1",
  "transcribedAt": "2026-05-26T12:00:00Z",
  "status": "success",
  "errorMsg": null
}

Requirements

  • OpenAI API key — Bring your own key at https://platform.openai.com/api-keys. Whisper pricing is approximately $0.006 per minute of audio (billed by OpenAI to your account).
  • Public audio URLs — Files must be publicly accessible without authentication.

Pricing

This actor charges $0.10 per start + $0.001 per file processed (including error records). OpenAI Whisper API costs are separate and billed directly to your OpenAI account.

Error handling

Files that fail to download or transcribe are not dropped — the actor saves an error record to the dataset with status: "error" and a descriptive errorMsg. This ensures your dataset always has one row per input URL for easy reconciliation.

Common errors:

  • HTTP 401 — Invalid API key
  • HTTP 429 — OpenAI rate limit exceeded (retry with fewer files or lower concurrency)
  • File exceeds 25 MB limit — Source file too large for Whisper API
  • Download timed out — URL not reachable within 60 seconds
Try on Apify