Alireza29675 / whisper-liveLinks
TypeScript-based library for real-time audio transcription, integrating OpenAI's Whisper model for accurate speech-to-text conversion.
☆69Updated last year
Alternatives and similar repositories for whisper-live
Users that are interested in whisper-live are comparing it to the libraries listed below
Sorting:
- An JS web client for connecting to Pipecat bots with voice and vision☆44Updated 5 months ago
- Shush is an app that deploys a WhisperV3 model with Flash Attention v2 on Modal and makes requests to it via a NextJS app☆205Updated 11 months ago
- Speech recognition & diarisation solution with text alignment, deployed in AML pipelines☆94Updated last year
- Real-Time Voice Inference Web SDK☆241Updated this week
- faster-whisper as serverless endpoint☆102Updated 2 weeks ago
- The JavaScript client for the Cartesia API.☆97Updated last month
- streaming speech to text server using Whisper☆92Updated 2 years ago
- WIP exploration using Twilio Media Streams and Generative AI☆40Updated last year
- web based editor for subtitles and transcripts☆133Updated 9 months ago
- Cog implementation of transcribing + diarization pipeline with Whisper & Pyannote☆212Updated 3 months ago
- Whisper realtime streaming for long speech-to-text transcription and translation☆117Updated last year
- ☆51Updated 8 months ago
- A bash script using OpenAI Whisper API for continuous audio transcription with automatic silence detection☆109Updated last year
- Live-Transcription (STT) with Whisper PoC☆183Updated 11 months ago
- An experiment of trying out whisper.cpp for real-time speech-to-text☆20Updated 2 years ago
- FastAPI service on top of WhisperX☆102Updated this week
- Real-Time Whisper Voice Recognition with vosk model feedback.☆112Updated last year
- Mobile web app for audio "push-to-talk" + TTS chat interface with OpenAI-like APIs☆43Updated last year
- kokoro text to speech using javascript☆57Updated 4 months ago
- Demo of AI chatbot that predicts user message to generate response quickly.☆102Updated last year
- A WebRTC server that allows you to interact with an LLM using your speech and responds back with generated audio.☆132Updated 11 months ago
- Record audio and save a transcription to your system's clipboard with ctranslate2 and faster-whisper.☆122Updated last month
- Blazing fast whisper turbo for ASR (speech-to-text) tasks☆208Updated 7 months ago
- Context-Aware Semantic Cache for Conversational AI☆25Updated 5 months ago
- Simulates talk with an AI that can express emotions☆69Updated 10 months ago
- Starter project for building real-time AI Voice Assistants☆38Updated 8 months ago
- a simple system for 2-way interruptible voice interactions between human and LLM☆29Updated last year
- ☆37Updated last year
- Record and stream WAV audio data in the browser across all platforms☆81Updated 6 months ago
- A mono-repo to house the various supported Transport options to be used with Pipecat's client-js package☆23Updated last week