WhisperLive
A nearly-live implementation of OpenAI's Whisper for real-time voice recognition
GraphCanon updated 3w · GitHub synced 3w
Decision brief
WhisperLive offers nearly real-time speech transcription based on OpenAI's Whisper model across multiple hardware-accelerated backends.
Good fit when
- When you require low-latency voice recognition and can leverage high-performance GPUs or OpenVINO for significant speedups.
- If your project specifically targets Linux systems like Debian, Ubuntu, Fedora, or macOS with Homebrew support for audio input setup.
Avoid when
- Avoid using WhisperLive if the project lacks necessary hardware acceleration via TensorRT, OpenVINO, or is deployed on environments not compatible with Docker configurations.
- Do not choose WhisperLive if a Windows-only solution is required, as its setup instructions are tailored for Linux and macOS.
- Requirements:
- Min 4 GB RAM; Requires Docker; PortAudio system dependency required.; Requires Python 3.12 environment and virtual environments
Observed Jul 17, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (1d since push)
- As of 3w
- Provenance
- Not a fork · Organization account
- As of 3w
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
pip install WhisperLiveHow it fits your stack(1)
Typed graph edges - alternatives, integrations, successors, and dependencies. Ranked by relationship type, not raw GitHub stars.
Relationship graph
Optional deeper exploration of typed edges and category neighbours.
Similar tools
Same-category neighbours not already linked as typed edges.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
WhisperLive provides an almost live transcription service based on the Whisper model by OpenAI, supporting multiple backends like Faster-Whisper, TensorRT, and OpenVINO for diverse performance needs.
Capability facts
- Languages
- python
Source: github.language · Jul 29, 2026
Categories
Compatibility
Sourced claims from the README excerpt - not unsourced marketing copy.
Source: README excerpt (regex_v1, Jul 29, 2026)
- Install 3.12 venv (on Fedora `sudo dnf install -y python3.12 python3.12-pip`)Source link
Tags
README
Installation
- Install PortAudio (required system dependency for microphone input via PyAudio)
bash scripts/setup.sh
On Debian/Ubuntu this installs portaudio19-dev, on Fedora portaudio-devel, on macOS it uses Homebrew (portaudio).
- Install 3.12 venv (on Fedora
sudo dnf install -y python3.12 python3.12-pip)
python3.12 -m venv whisper_env
source whisper_env/bin/activate
- Install whisper-live from pip
pip install whisper-live
Getting Started
The server supports 3 backends faster_whisper, tensorrt and openvino. If running tensorrt backend follow TensorRT_whisper readme
Whisper Live Server in Docker
-
GPU
- Faster-Whisper
docker run -it --gpus all -p 9090:9090 ghcr.io/collabora/whisperlive-gpu:latest- TensorRT. Refer to TensorRT_whisper readme for setup and more tensorrt backend configurations.
docker build . -f docker/Dockerfile.tensorrt -t whisperlive-tensorrt docker run -p 9090:9090 --runtime=nvidia --gpus all --entrypoint /bin/bash -it whisperlive-tensorrt # Build small.en engine bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en # float16 bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en int8 # int8 weight only quantization bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en int4 # int4 weight only quantization # Run server with small.en (pick one engine) python3 run_server.py --port 9090 \ --backend tensorrt \ --trt_model_path "/app/TensorRT-LLM-examples/whisper/whisper_small_en_float16" # or int8 / int4: # --trt_model_path "/app/TensorRT-LLM-examples/whisper/whisper_small_en_int8" # --trt_model_path "/app/TensorRT-LLM-examples/whisper/whisper_small_en_int4"- OpenVINO
docker run -it --device=/dev/dri -p 9090:9090 ghcr.io/collabora/whisperlive-openvino- AMD ROCm (faster-whisper on AMD GPU via CTranslate2 ROCm wheel)
docker build -f docker/Dockerfile.rocm -t whisperlive-rocm . docker run --rm -it --device=/dev/kfd --device=/dev/dri \ --group-add "$(getent group video | cut -d: -f3)" \ --group-add "$(getent group render | cut -d: -f3)" \ -p 9090:9090 whisperlive-rocm -
CPU
- Faster-whisper
docker run -it -p 9090:9090 ghcr.io/collabora/whisperlive-cpu:latest
For agents
This page has a .md twin and JSON over the API.