Automatic Speech Recognition (ASR)
Turn audio and video submissions into transcripts. ASR helps teachers scan student speech, support feedback, compare progress, and make spoken work easier to revisit.
Models: AssemblyAI Universal-2 (universal-2) for recordings; Universal Streaming Multilingual (universal-streaming-multilingual) for live transcription.
Languages for recorded audio and video
- Arabic
- Bengali
- Czech
- Danish
- Dutch
- English
- Finnish
- French
- German
- Greek
- Gujarati
- Hebrew
- Hindi
- Hungarian
- Indonesian
- Italian
- Japanese
- Kannada
- Korean
- Malay
- Malayalam
- Mandarin Chinese
- Marathi
- Norwegian
- Polish
- Portuguese
- Punjabi
- Romanian
- Russian
- Slovak
- Spanish
- Swedish
- Tagalog
- Tamil
- Turkish
- Ukrainian
- Urdu
- Vietnamese
ASR includes Global English, US English, and British English options. Live transcription supports English, French, German, Italian, Portuguese, and Spanish; the other languages support transcription after recording.