Audio & Video Transcription: Whisper, Podcasts, SRT/VTT
Pricing
from $10.00 / 1,000 audio minutes
Audio & Video Transcription: Whisper, Podcasts, SRT/VTT
Pricing
from $10.00 / 1,000 audio minutes
Direct links to audio or video files (mp3, m4a, wav, mp4, webm…), podcast RSS feeds, or Apple Podcasts links. Feeds and Apple links transcribe their latest episodes. Video and social platforms (YouTube, TikTok…) are not supported.
Bigger models are more accurate and slower. Fast and Balanced cost the same per minute; Accurate uses about 3x the computing power, so each minute counts as 3.
Two-letter code such as en, es, ja. Leave empty to detect automatically.
Output English text for speech in any language (Whisper's built-in translation). Same price. "language" in the result is the spoken language.
Add start/end time and confidence for every word (for captions, karaoke-style subtitles and editing). Slightly slower, same price.
Latest episodes to transcribe for each feed or Apple link.
Longer files are skipped (not charged).