Whisper is OpenAI's open-source automatic speech recognition (ASR) model trained on 680,000 hours of multilingual data. Supports transcription in 99+ languages, translation to English, and word-level timestamps. Widely self-hosted and integrated into products like ChatGPT, Descript, and dozens of API services.
Whisper Functions
Technical Specifications
Features
Real-Time, API Access, Self-Hosted, Offline Mode, Batch Processing, Streaming
Input Types
Audio, Voice, Video
Output Types
Text, JSON
Platforms
Web, Windows, macOS, Linux
Interface Types
API, CLI Tool
Customization
API/SDK, Fully Customizable
Language Support
Multilingual
Compliance
Data Privacy, Local Deployment, On-Premise
Autonomy Level
Assistant Mode
Target Audience
Developers, Enterprise, Researchers, Individuals