Audio & Video to Text Converter: Transcribe Files, Whisper avatar

Audio & Video to Text Converter: Transcribe Files, Whisper

Pricing

from $2.10 / 1,000 audio minute transcribeds

Go to Apify Store
Audio & Video to Text Converter: Transcribe Files, Whisper

Audio & Video to Text Converter: Transcribe Files, Whisper

Audio to text converter for any file or link: transcribe YouTube videos, MP3, MP4 and WAV files, Google Drive or Dropbox links, TikTok, Instagram, Loom or SoundCloud posts, or another Actor's results. Transcript, timestamps and SRT in 99+ languages. Pay per minute.

Pricing

from $2.10 / 1,000 audio minute transcribeds

Rating

0.0

(0)

Developer

clement

clement

Maintained by Community

Actor stats

0

Bookmarked

7

Total users

1

Monthly active users

2 days ago

Last modified

Categories

Features

Limited permissions

Share

What is Audio & Video to Text?

Audio & Video to Text turns any recording into accurate text. Paste a file link, a Google Drive or Dropbox share link, a public YouTube, TikTok, Instagram, Loom, Twitch or SoundCloud link, or upload a file, and get the transcript as plain text, timestamped segments and SRT subtitles.

Try it now: the example below transcribes a short speech in a few seconds.

What can this speech-to-text tool do?

  • Any common format. MP3, M4A, WAV, OGG, FLAC, AAC, MP4, MOV, WEBM and more. For video, the audio track is transcribed.
  • Public video links. TikTok, Instagram, Loom, Twitch and SoundCloud posts work directly, with their public details.
  • 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.
  • Pay per audio minute. No subscription, and nothing charged for files that fail or hold no speech.

Because it runs on Apify, you also get:

  • Scheduling: transcribe new recordings on a regular basis.
  • API access: start runs and read results from your own code.
  • Integrations: send results to Make, Zapier, n8n, Google Sheets and more.
  • Monitoring: get alerted when a run fails or returns less than expected.
  • Exports: download results as JSON, CSV or Excel.

What can you provide?

InputExample
Direct file linkhttps://example.com/interview.mp3
Google Drive share linkhttps://drive.google.com/file/d/FILE_ID/view
Dropbox share linkhttps://www.dropbox.com/scl/fi/.../meeting.mp4?rlkey=...
Public post on TikTok, Instagram, Loom, Twitch or SoundCloudhttps://www.loom.com/share/VIDEO_ID
File uploadUse the Or upload a file field

Share links must be set to "anyone with the link can view". Platform links must point to one public post, not a profile. You can mix several links in one run. For platform posts, each result also carries the creator, caption and public counts.

How to transcribe audio or video

  1. Get a link to your file: a direct file URL, a Google Drive or Dropbox link shared with "anyone with the link", or a public post 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.

How much does it cost to transcribe audio?

You pay for each minute of audio transcribed, rounded to the nearest minute, with a minimum of one minute per file. The price depends on your Apify Store discount tier:

Store discount tierPrice per audio minute
Free plan$0.003
Bronze$0.0027
Silver$0.0024
Gold and above$0.0021

At the Bronze price:

AudioCost
A 30-minute meeting$0.081
A 1-hour interview$0.162
100 one-minute clips$0.27

Files that fail or hold no speech are not charged. 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.

On the free Apify plan, each run transcribes up to 10 minutes of audio in total: longer audio is cut there and marked "truncated": true. Paid Apify plans have no such limit.

Input example

{
"urls": [
"https://api.apify.com/v2/key-value-stores/kyR7mGkrVQ6H3xQe8/records/jfk-we-choose-the-moon.mp3?signature=1IsTRMMS6FEWC0SVKQvL6"
],
"includeSegments": true
}
FieldMeaning
urlsFile links, share links or public post links
fileA file uploaded from your computer, instead of a link
languageTwo-letter language code (optional; detected automatically otherwise)
includeSegmentsAdd timestamped segments to each result
includeSrtAdd the transcript as SRT subtitles
maxMinutesPerFileLonger files are cut at this length

Output example

A real result for the input above, with the list of segments shortened. One dataset item per file:

{
"inputUrl": "https://api.apify.com/v2/key-value-stores/kyR7mGkrVQ6H3xQe8/records/jfk-we-choose-the-moon.mp3?signature=1IsTRMMS6FEWC0SVKQvL6",
"status": "ok",
"fileName": "jfk-we-choose-the-moon.mp3",
"language": "English",
"durationSeconds": 20,
"transcribedMinutes": 1,
"truncated": false,
"text": "We choose to go to the moon in this decade and do the other things. Not because they are easy, but because they are hard. 3, 2, 1, 0. All engines running. Liftoff. We have a liftoff. 32 minutes past the hour. Liftoff on Apollo 11.",
"segments": [
{
"start": 0,
"end": 4.1,
"text": "We choose to go to the moon in this decade and do the other things."
}
]
}

segments is included by default; srt is included when Include SRT subtitles is on. Each result then also carries the creator, caption and public counts.. Audio with no speech comes back with "noSpeech": true and is not charged. Files that cannot be processed produce an item with "status": "error" and an error message explaining why.

Use cases

  • Meetings and interviews: transcribe calls, lectures and voice memos.
  • Video: create SRT subtitles and text versions of your videos.
  • Search and notes: turn recordings into searchable text.
  • AI workflows: feed transcripts to an LLM for summaries and analysis.
  • Archives: batch-process a library of recordings through the API.

Tips for better transcripts

  • Set the language for short or noisy audio. Automatic detection works best with a few seconds of clear speech.
  • Use clear audio. Background music and people talking over each other cause most mistakes.
  • Cap your spending. Set the maximum minutes, or the run's maximum charge, before processing a large batch.
  • Share links must be open: set Google Drive and Dropbox files to "anyone with the link can view".

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 about $0.135 at the Bronze price. Nothing is 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.

Yes. Public posts on TikTok, Instagram, Loom, Twitch and SoundCloud work directly. Each result also carries the creator, caption and public counts.

Can I transcribe a YouTube video?

Yes. Public YouTube videos and Shorts are read by Google's Gemini model, since YouTube does not let this Actor download them. The text is word for word; times are given to the second and can be a little less precise than for uploaded files. Private, age-restricted and region-locked videos cannot be read and are not charged. Vimeo and Facebook still need a login: download the recording first, then upload it or share it through Google Drive or Dropbox.

Can I transcribe the results of another Actor?

Yes. Under Or: links from another Actor's results, pick the dataset of a scraper run (TikTok, Instagram or YouTube scrapers, or any list of file links). Every link in it is transcribed, so this Actor can follow a scraper in a pipeline.

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

Yes. Call it through the Apify API (see the examples 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.

Limits

  • All users share one transcription service with an hourly limit. When it is reached, the Actor stops at once and returns what it has finished, marked "truncated": true and charged only for that part, with a note saying when to try again.
  • Links must point to a file, or to one public post on YouTube, TikTok, Instagram, Loom, Twitch or SoundCloud. Vimeo and Facebook links are not supported.
  • Platforms occasionally refuse a request. The Actor retries once; if it still fails, the item is reported as an error and not charged.
  • 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.

Other Actors you may find useful

ActorWhat it does
Podcast SummaryAn AI summary, chapters, quotes and show notes for each episode, with the transcript
Spotify Podcast TranscriptTranscripts of Spotify, Apple Podcasts and Deezer episodes
Subtitle GeneratorSRT and VTT subtitle files, ready for your editor
TikTok TranscriptWhat is said in TikTok videos, with creator and public counts
Instagram Reels TranscriptWhat is said in Instagram Reels, with creator and public counts
PDF & Image to TextText from PDFs, scans, photos and screenshots

Run it from the API

With cURL:

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://api.apify.com/v2/key-value-stores/kyR7mGkrVQ6H3xQe8/records/jfk-we-choose-the-moon.mp3?signature=1IsTRMMS6FEWC0SVKQvL6"], "includeSrt": true }'

With Python:

from apify_client import ApifyClient
client = ApifyClient("YOUR_TOKEN")
run = client.actor("spokentext/audio-video-to-text").call(run_input={"urls": ["https://api.apify.com/v2/key-value-stores/kyR7mGkrVQ6H3xQe8/records/jfk-we-choose-the-moon.mp3?signature=1IsTRMMS6FEWC0SVKQvL6"]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
print(item["text"][:100])

This Actor is an independent tool. It is not affiliated with or endorsed by Google, Dropbox, TikTok, Instagram, Meta, Loom, Twitch or SoundCloud; their names only describe the links it accepts.

Feedback

Something failed or gave a wrong result? Open an issue in the Issues tab of this page, with the error message from your results: every report is read and fixed. If the Actor saved you time, a rating helps others find it.