Audio & Video to Text: Whisper Transcription & SRT Subtitles

Turn any audio or video file into accurate text. Paste a file link, a Google Drive or Dropbox share link, or upload a file, and get the transcript as plain text, timestamped segments and SRT subtitles.

• Any common format. MP3, M4A, WAV, OGG, FLAC, AAC, MP4, MOV, WEBM and more. For video, the audio track is transcribed.
• Pay per audio minute. No subscription, and nothing charged for files that fail.
• 99+ languages with automatic language detection (Whisper large-v3).
• Fast. One hour of audio is typically ready in about a minute.
• Long recordings handled. Files are split and stitched back together automatically. Recordings up to about 2 hours are supported, in files up to 1.5 GB.

What you can provide

Input	Example
Direct file link	https://example.com/interview.mp3
Google Drive share link	https://drive.google.com/file/d/FILE_ID/view
Dropbox share link	https://www.dropbox.com/scl/fi/.../meeting.mp4?rlkey=...
File upload	Use the Or upload a file field

Share links must be set to "anyone with the link can view". You can mix several links in one run.

How to use

1. Get a link to your file: a direct file URL, or a Google Drive or Dropbox link shared with "anyone with the link". Or skip links and use Or upload a file.
2. Paste the link into Audio or video file URLs. Add as many as you like.
3. Optionally set the language or turn on SRT subtitles.
4. Click Start. When the run finishes, open the Output tab and download the transcripts as JSON, CSV or Excel.

Output

One dataset item per file:

{
    "inputUrl": "https://example.com/interview.mp3",
    "status": "ok",
    "fileName": "interview.mp3",
    "language": "English",
    "durationSeconds": 1842,
    "transcribedMinutes": 31,
    "truncated": false,
    "text": "Thanks for joining me today. Let's start with...",
    "segments": [{ "start": 0, "end": 3.4, "text": "Thanks for joining me today." }],
    "srt": "1\n00:00:00,000 --> 00:00:03,400\nThanks for joining me today.\n"
}

segments is included by default; srt is included when Include SRT subtitles is on. Files that cannot be processed produce an item with "status": "error" and an error message explaining why.

Pricing

You pay for each minute of audio transcribed, rounded to the nearest minute (minimum one minute per file). Set Maximum minutes per file or the run's maximum charge to cap spending: the Actor stops before exceeding either, and marks a cut file with "truncated": true.

Use cases

• Transcribe interviews, meetings, lectures, calls and voice memos.
• Create SRT subtitles for videos.
• Turn recordings into searchable notes, or feed them to an LLM for summaries and analysis.
• Batch-process an archive of recordings through the API.

Limits

• Links must point to a file, not a web page. YouTube, TikTok and other video-page links are not supported.
• For podcasts, use Spotify Podcast Transcript, which accepts Spotify, Apple Podcasts and RSS links.
• No speaker labels: the transcript does not say who is speaking.
• Private files that require a login cannot be read. Upload them instead.

FAQ

How do I convert an audio file to text?

Paste a link to the file (MP3, M4A, WAV and more) or upload it, then start the run. The transcript appears in the Output tab, with timestamps for every sentence.

How do I transcribe a video to text?

The same way. For MP4, MOV, WEBM and other video files the Actor reads the audio track and ignores the picture, so large videos are handled quickly.

How long does it take and how much does it cost?

A 50-minute recording takes about 40 seconds and costs $0.15. Price is $0.003 per audio minute, with nothing charged for files that fail.

How accurate is the transcript?

It uses Whisper large-v3. Clear speech comes out very accurately; names, jargon, heavy background noise and people talking over each other can contain mistakes. The transcript does not label speakers.

Which languages are supported?

More than 99, detected automatically. For short or noisy audio, setting the language code (en, fr, es, de...) improves accuracy.

Can I transcribe long recordings?

Yes, up to about 2 hours per recording. The file is split into parts, transcribed and stitched back together with continuous timestamps. Cut longer recordings into parts of under 2 hours first.

Can I transcribe a YouTube or TikTok link?

No. Links must point to a file. Download or export the recording first, then upload it or share it through Google Drive or Dropbox.

Can I use it from my own code, Make, Zapier or n8n?

Yes. Call it through the Apify API (see the example below), or connect it with Apify's integrations for Make, Zapier and n8n. Every run returns the same JSON.

What happens to my file?

The file is downloaded during the run, its audio is sent to our speech-to-text provider (Groq) to be transcribed, and it is deleted when the run ends. Transcripts are stored only in your own Apify account.

Run it from the API

curl -X POST "https://api.apify.com/v2/acts/spokentext~audio-video-to-text/run-sync-get-dataset-items?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ "urls": ["https://example.com/interview.mp3"], "includeSrt": true }'