Software · Intermediate
Whisper
OpenAI's open speech-to-text model that transcribes audio accurately across many languages.
Whisper is OpenAI's automatic speech recognition model, released openly so it powers countless transcription and captioning tools. It handles accents, background noise, and dozens of languages with strong accuracy, and can translate speech to English. Creators use it, directly or through apps built on it, to generate transcripts, subtitles, and searchable text from their video and audio.
Also called OpenAI Whisper, Whisper AI
Related
- Auto-CaptionsAI-generated on-screen captions transcribed automatically from your audio.
- Podcast TranscriptA written version of an episode for accessibility and search.
- DescriptEditor that lets you cut audio and video by editing an auto-generated transcript.
- Show NotesThe written description and links that accompany an episode in podcast apps.
- CaptionsMobile-first app that adds animated captions and AI edits to talking-head videos.