AssemblyAI-STT-3.7
Recorded audio. Typically handles 32 languages, with optional fallback covering 99 languages.
Specifications
- Released
- Nov 18, 2026
- Inputs
- Audio
- Weights
- Weights unconfirmed
- Task
- Speech recognition
- Published capabilities
- Recorded audio. Typically handles 32 languages, with optional fallback covering 99 languages.
- Access
- Pre-recorded Speech-to-Text API as assemblyai-stt-3-7
- Result
- Batch transcript with speaker labels
- Billing terms
- $0.21 USD per hour of audio on AssemblyAI.