Whisper is an open-source automatic speech recognition system by OpenAI trained on 680,000 hours of multilingual web audio data, offering near human-level robustness and accuracy in English and 99 other languages. It is available on GitHub and via the OpenAI API.
Category
Audio & Music
Subcategory
Speech-to-Text
Free Tier
Free open-source model
Paid Plans
Not available yet
API Cost
$0.006/min via OpenAI API
APICLI
● certified · ○ not verified
Compliance data is community-sourced and may be incomplete or out of date. Always verify certifications directly with the vendor's official trust or security page before relying on them.
Self-hostable
Yes
Some data-handling details aren't verified yet. Help verify this data ↗
Transcribing audio files offline and locallyBuilding speech-to-text applications with APIConverting multilingual audio to textGenerating closed captions for video contentIntegrating speech recognition into custom workflows
// MORE IN SPEECH-TO-TEXT
Audio & MusicSpeech-to-Text
#speech-to-text api#transcription api
Audio & MusicSpeech-to-Text
#speech recognition api#real-time transcription
Audio & MusicSpeech-to-Text
#transcription api#speech-to-text