Transcribe an audio file to text
Fast recognition of a 4-minute conversation.
{
"urls": [
"https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/conversation-4min.ogg"
],
"quality": "fast"
}Speech to text
Audio Transcriber: podcasts, calls and meetings to text with timecodes
Turn recordings into text in 90+ languages, with a timecode on every passage. Send a file of any length, a podcast or video link, and optionally add speaker labels, subtitle files, English translation or chunks ready for retrieval.
★ 5.0 rating · 2 reviews15 users95.5% successful runs (30 days)
What data you get
transcript | Full transcript text |
segments | Passages with start time and duration |
speakers | Optional speaker labels per segment |
language | Detected or chosen language |
subtitles | Optional SRT or VTT file as text |
chunks | Optional RAG chunks with start timecodes |
translation | Optional English transcript |
duration | Length of the recording |
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: a charge per file processed and per minute transcribed, with a lower per-minute rate if you bring your own Groq key. Video links and speaker labels are separate add-on events.
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 interview with speaker labels and SRT subtitles
Two speakers, English, subtitle file included.
{
"urls": [
"https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/conversation-4min.ogg"
],
"diarize": true,
"speakerCount": 2,
"language": "en",
"subtitleFormat": "srt"
}Transcribe a YouTube video into RAG chunks
Accurate mode with timecoded chunks for retrieval.
{
"urls": [
"https://www.youtube.com/watch?v=dQw4w9WgXcQ"
],
"quality": "accurate",
"chunkForRag": true,
"chunkSize": 1200,
"chunkOverlapSeconds": 5
}Transcribe and translate audio to English
English output with a vocabulary hint for names.
{
"urls": [
"https://raw.githubusercontent.com/lergassy/apify-actor-assets/main/audio-samples/conversation-4min.ogg"
],
"translateToEnglish": true,
"vocabularyHint": "Apify, Lergassy, RAG"
}Use cases
- Podcasters and creators: get show notes, quotes and subtitles from every episode.
- Sales and support teams: turn recorded calls into searchable text.
- Researchers and journalists: transcribe interviews with speaker labels and timecodes.
- AI builders: feed timecoded chunks of audio content into RAG pipelines.
FAQ
Which languages are supported?
90+ languages, detected automatically or set with a two-letter code. You can also get an English transcript whatever the spoken language.
What inputs can I use?
Direct audio or video file URLs, an uploaded file, or links from platforms such as YouTube, TikTok, Instagram, Vimeo and SoundCloud.
Can it tell speakers apart?
Yes. Turn on speaker labels and every segment gets a speaker; set the number of speakers if you know it.
Is it legal to transcribe recordings?
Only transcribe audio you own or have permission to use, and get consent from call participants where the law requires it. Handle any personal data in transcripts according to privacy laws.
How do I integrate it?
Use the Apify API, Python or JavaScript clients, or connect to Make, n8n, Zapier or Google Sheets.