AI transcription

Audio to Text: transcribe audio files into timed transcripts

Paste links to MP3, M4A, WAV, FLAC or OGG files, or upload one, and get a timed transcript in 90+ languages. Add speaker labels, translate to English, export SRT or VTT subtitles, or split the text into chunks ready for RAG.

3 users100.0% successful runs (30 days)

Run on Apify — free trial Use via API

What data you get

`text`	Full transcript text
`segments`	Timed segments with start and end
`language`	Detected spoken language
`speakers`	Speaker labels (optional add-on)
`translation`	English translation (optional)
`subtitles`	SRT or VTT subtitle file
`chunks`	RAG-ready text chunks

How it works

Open the scraper on Apify and sign up (free).
Enter routes, dates and options in the form.
Click Start and download results as JSON, CSV or Excel, or call the API.

Pricing

$2.00 per 1,000 rows

Pay per event: you are charged per minute of audio transcribed plus a small fee per file processed. Speaker labels are an optional add-on per minute, and minutes are cheaper with your own Groq API key; there is no per-run fee.

Apify gives $5 free credits every month — enough to test this scraper at no cost.

Example tasks

Ready-made inputs. Copy one into the scraper form or send it through the API.

Transcribe an M4A file to SRT subtitles

Accurate mode with an SRT subtitle file.

{
  "urls": [
    "https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
  ],
  "quality": "accurate",
  "subtitleFormat": "srt"
}

Run this task →

Interview transcription with speaker labels

Two speakers plus a vocabulary hint for brand names.

{
  "urls": [
    "https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
  ],
  "diarize": true,
  "speakerCount": 2,
  "vocabularyHint": "Apify, scraper, dataset"
}

Run this task →

Translate audio to English text

Any spoken language transcribed and translated to English.

{
  "urls": [
    "https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
  ],
  "translateToEnglish": true
}

Run this task →

Split an audio transcript into RAG chunks

1,500-character chunks with 5 seconds of overlap.

{
  "urls": [
    "https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/sample-1min.m4a"
  ],
  "chunkForRag": true,
  "chunkSize": 1500,
  "chunkOverlapSeconds": 5
}

Run this task →

Use cases

Podcasters: turn episodes into searchable transcripts and show notes.
Researchers: transcribe interviews with speaker labels for coding and analysis.
AI developers: feed recordings into RAG pipelines as ready-made text chunks.
Customer support teams: convert call recordings into text for quality review.

FAQ

Which audio formats are supported?

MP3, M4A, WAV, FLAC and OGG, either as links or as an uploaded file.

Which languages does it transcribe?

More than 90 languages. Set the two-letter language code, or leave it empty to detect it automatically.

Can it tell speakers apart?

Yes. Turn on speaker labels and optionally set the number of speakers.

Is it legal to transcribe audio files?

Transcribe only recordings you own or have permission to use, respect copyright and local recording-consent laws, and handle any personal data in them carefully.

How do I integrate it?

Use the Apify API, Python or JavaScript clients, or integrations with Make, n8n, Zapier and Google Sheets.

More scrapers

Whisper TranscriberAI transcription Video to TextAI transcription MP3 to TextAI transcription Threads ScraperSocial media data Google Flights ScraperTravel data Shopee ScraperE-commerce data

Transcribe your first audio file now

Run on Apify — free trial