Whissle
Provides access to Whissle API endpoints for speech-to-text, diarization, translation, and text summarization.
About
Whissle provides a Python-based server interface for accessing Whissle's powerful API functionalities. Seamlessly integrate speech-to-text, diarization, translation, and text summarization capabilities into your projects. The server handles audio file processing, authentication, and provides a straightforward API for various tasks, ensuring easy integration and efficient access to Whissle's services.
Key Features
- Text translation between multiple languages
- Comprehensive error handling with automatic retries and detailed error messages
- 1 GitHub stars
- Text summarization using LLM models
- Speech-to-text conversion with word timestamps and boosted language model support
- Speech diarization to identify speakers in audio
Use Cases
- Real-time translation of spoken conversations
- Summarization of large text documents
- Automated transcription of audio files