1.4.0 (2025-06-04)
Features Added
- Real-time transcription support
- Audio and DTMF streaming capabilities
- Integration of ConnectAPI for seamless streaming and transcription
- Improved media streaming with bidirectional functionality, allowing audio formats in both directions, currently supporting sample rates of 24kHz and 16kHz
- Support for custom speech models has been integrated into transcription
- A confidence level for recognized speech has been introduced, ranging from 0.0 to 1.0 when available