Audio Transcription (Whisper): Speech to Text, SRT and VTT
Pricing
Pay per usage
Go to Apify Store
Audio Transcription (Whisper): Speech to Text, SRT and VTT
Pricing
Pay per usage
Rating
0.0
(0)
Developer
Venture Ace
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
2 hours ago
Last modified
Share
Audio Transcription (Whisper)
Speech to text for audio and video files from direct URLs, using Whisper (faster-whisper, CTranslate2, MIT) on CPU.
- Input:
files(direct file URLs),model(basedefault,small),language(auto),outputFormats(segments,srt,vtt; text is always returned),maxAudioMinutes(default 60, total per run). - Output: one dataset row per file:
url, status (ok | failed | too_long), error, language, durationSec, text, segments, srt, vtt. - One bad file (dead link, not audio, page URL, too large) gives a
failedrow with the reason; the run continues with the next file. - YouTube, TikTok, Instagram and other page URLs are refused. Localhost, private, link-local and CGNAT addresses are refused on every request and every redirect hop.
- No speaker diarization. Pricing: pay per usage of the platform (no actor fee yet);
smallcosts about 2-3 timesbase. - Speed: on the default 2 GB memory
baseruns at roughly 2x real time (one hour of audio takes about 30 minutes);smallis 2-3 times slower. The run stops at the Actor timeout, so forsmallor long lists lowermaxAudioMinutesor raise the timeout. A timeout or out-of-memory kill ends the run; only per-file problems are caught asfailedrows. - Accuracy depends on audio quality and language;
baseis weakest on non-English and noisy audio. - Licences: Whisper code and weights MIT, faster-whisper MIT, CTranslate2 MIT; ffmpeg (Debian package, GPL build) is run as a separate program and not linked or redistributed.
Local test: python -m unittest src/test_guard.py from this folder.
