whereismyai
WhisperLive
WhisperLive is a real-time transcription application that uses the OpenAI Whisper model to convert speech input into text output.
WhisperLive is a real-time transcription application utilizing the OpenAI Whisper model to convert speech into text. It supports live microphone input, pre-recorded audio files, RTSP streams, HLS streams, and raw PCM input. Users can run the server using backends such as faster-whisper, TensorRT, and OpenVINO, with Docker recommended for TensorRT and OpenVINO deployments. Advanced features include word-level timestamps, custom vocabulary hotwords, speaker diarization via pyannote.audio, and batch inference. The application also provides browser extensions for Chrome and Firefox, alongside an iOS client. It is designed for developers and users needing near-live speech recognition and translation capabilities.
WhisperLive at a glance
- Best for: Software engineer
- Runs on: Web, iOS, Chrome extension, API, self-hosted, open source
- Pricing: Free
- Released: May 2023
- Category: AI audio tool
- Website: github.com/collabora/WhisperLive
Key features
- Real-time transcription
- Word-level timestamps
- Custom vocabulary and hotwords
- Speaker diarization
- Batch inference
- Raw PCM input support
- Streaming client with manual audio chunking
Use it for
- Transcribe live microphone audio in real time
- Convert pre-recorded audio files to text
- Process RTSP and HLS audio streams
- Identify speakers using diarization
- Translate spoken audio into target languages
Alternatives to WhisperLive
- browser-whisper — Transcribes audio and video locally with zero servers involved.
- WhisperX — It enables 70x faster, batched transcription with high-accuracy alignment.
- faster-whisper — Transcribes audio faster with lower memory usage than standard implementations.
- Whisper ASR Webservice — Provides a REST API for multiple ASR engines including WhisperX and Faster Whisper.
- Whisper Timestamped — Generates accurate word-level timestamps without extra neural networks.
- Whisper Diarization — Combines OpenAI Whisper with voice activity detection and speaker embedding.
- whisper.cpp — It provides high-performance, offline speech recognition on diverse hardware.
- talkflow — Transcribes speech entirely on your device with no word limits or cloud accounts
- AssemblyAI — Industry-leading speech models deliver high accuracy and low latency for voice applications.
- RealtimeSTT — Provides fast local speech recognition with voice activity detection and wake words.
- Speech-to-Speech — Fully modular, swappable components with local or hosted execution options.
- Esp32 Pie ASR — Faster than real time streaming speech recognition on a microcontroller alone
All WhisperLive alternatives