SevaSk/ecoute
Ecoute
Ecoute is a live transcription tool that provides real-time transcripts for both the user's microphone input (You) and the user's speakers output (Speaker) in a textbox.
Features
- Real-Time Transcription - Captures both microphone input and speaker output simultaneously to display live text transcripts of a conversation.
- Local Speech-to-Text - Transcribes audio files using a local speech recognition model that runs on your own hardware.
- Speech Recognition Engines - Runs a pre-trained speech-to-text model directly on the user's hardware for offline transcription.
- Combined Microphone and System Audio Captures - Captures both microphone input and system speaker output simultaneously for real-time conversation transcription.
- Transcription Provider Switching - Switches between local and API transcription backends at runtime based on user preference.
- Speech Recognition APIs - Sends audio to a remote cloud speech recognition service via HTTP requests for transcription.
- Speech-to-Text Integrations - Sends audio to a remote API for transcription, enabling broader language support and offloading processing.
- Speech to Text Transcription - Sends audio files to a remote speech-to-text service for processing and receives transcribed text.
- Offline Transcript Processors - Transcribes audio files or live speech using a local model when internet access is unavailable or privacy is a concern.
- Real-Time Transcription Pipelines - Processes incoming audio chunks continuously through a buffered stream for live text output.
- Speech-to-Text API Wrappers - Transcribes audio by sending it to a remote speech recognition service for processing.
