{"data":{"slug":"collabora-whisperlive","name":"WhisperLive","tagline":"A nearly-live implementation of OpenAI's Whisper for real-time voice recognition","github_url":"https://github.com/collabora/WhisperLive","owner":"collabora","repo":"WhisperLive","owner_avatar_url":"https://avatars.githubusercontent.com/u/4499761?v=4","primary_language":"Python","stars":4190,"forks":574,"topics":["dictation","obs","openai","openvino","openvino-intel","rocm","tensorrt","tensorrt-llm","text-to-speech","translation","voice-recognition","whisper","whisper-tensorrt"],"archived":false,"github_pushed_at":"2026-07-27T20:39:23+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/collabora-whisperlive","markdown_url":"https://www.graphcanon.com/tools/collabora-whisperlive.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/collabora-whisperlive","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=collabora-whisperlive","description":"A nearly-live implementation of OpenAI's Whisper.","homepage_url":null,"license":"MIT","open_issues":37,"watchers":41,"ai_summary":"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.","readme_excerpt":"## Installation\n- Install PortAudio (required system dependency for microphone input via PyAudio)\n```bash\n bash scripts/setup.sh\n```\nOn Debian/Ubuntu this installs `portaudio19-dev`, on Fedora `portaudio-devel`, on macOS it uses Homebrew (`portaudio`).\n\n- Install 3.12 venv (on Fedora `sudo dnf install -y python3.12 python3.12-pip`)\n\n```bash\npython3.12 -m venv whisper_env\nsource whisper_env/bin/activate\n```\n\n- Install whisper-live from pip\n```bash\n pip install whisper-live\n```\n\n---\n\n## Getting Started\nThe server supports 3 backends `faster_whisper`, `tensorrt` and `openvino`. If running `tensorrt` backend follow [TensorRT_whisper readme](https://github.com/collabora/WhisperLive/blob/main/TensorRT_whisper.md)\n\n---\n\n## Whisper Live Server in Docker\n- GPU\n  - Faster-Whisper\n  ```bash\n  docker run -it --gpus all -p 9090:9090 ghcr.io/collabora/whisperlive-gpu:latest\n  ```\n\n  - TensorRT. Refer to [TensorRT_whisper readme](https://github.com/collabora/WhisperLive/blob/main/TensorRT_whisper.md) for setup and more tensorrt backend configurations.\n  ```bash\n  docker build . -f docker/Dockerfile.tensorrt -t whisperlive-tensorrt\n  docker run -p 9090:9090 --runtime=nvidia --gpus all --entrypoint /bin/bash -it whisperlive-tensorrt\n\n  # Build small.en engine\n  bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en        # float16\n  bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en int8   # int8 weight only quantization\n  bash build_whisper_tensorrt.sh /app/TensorRT-LLM-examples small.en int4   # int4 weight only quantization\n\n  # Run server with small.en (pick one engine)\n  python3 run_server.py --port 9090 \\\n                        --backend tensorrt \\\n                        --trt_model_path \"/app/TensorRT-LLM-examples/whisper/whisper_small_en_float16\"\n  # or int8 / int4:\n  # --trt_model_path \"/app/TensorRT-LLM-examples/whisper/whisper_small_en_int8\"\n  # --trt_model_path \"/app/TensorRT-LLM-examples/whisper/whisper_small_en_int4\"\n  ```\n\n  - OpenVINO\n  ```\n  docker run -it --device=/dev/dri -p 9090:9090 ghcr.io/collabora/whisperlive-openvino\n  ```\n\n  - AMD ROCm (faster-whisper on AMD GPU via CTranslate2 ROCm wheel)\n  ```bash\n  docker build -f docker/Dockerfile.rocm -t whisperlive-rocm .\n  docker run --rm -it --device=/dev/kfd --device=/dev/dri \\\n      --group-add \"$(getent group video | cut -d: -f3)\" \\\n      --group-add \"$(getent group render | cut -d: -f3)\" \\\n      -p 9090:9090 whisperlive-rocm\n  ```\n\n- CPU\n  - Faster-whisper\n  ```bash\n  docker run -it -p 9090:9090 ghcr.io/collabora/whisperlive-cpu:latest\n  ```","github_created_at":"2023-05-04T16:36:09+00:00","created_at":"2026-07-11T12:07:15.75642+00:00","updated_at":"2026-07-29T12:00:29.639596+00:00","categories":[{"slug":"speech-audio","name":"Speech & Audio","url":"https://www.graphcanon.com/categories/speech-audio","markdown_url":"https://www.graphcanon.com/categories/speech-audio.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/speech-audio"}],"tags":[{"slug":"dictation","name":"dictation"},{"slug":"text-to-speech","name":"text-to-speech"},{"slug":"translation","name":"translation"},{"slug":"voice-recognition","name":"voice-recognition"}],"trust":{"provenance":{"is_fork":false,"github_id":636344889,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-29T12:00:28.915Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":1,"days_since_push":1,"last_release_at":"2026-06-02T06:25:05Z"},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T12:07:18.537Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-29T12:00:29.363Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-07-29T12:00:29.363Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-29T12:00:29.363Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["PortAudio system dependency required.","Requires Python 3.12 environment and virtual environments"],"min_ram_gb":4,"requires_docker":true},"constraints":{"min_ram_gb":4,"requires_docker":true},"when_to_use":["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."],"when_not_to_use":["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."],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:47:46.390Z"},"constraint_facets":{"min_ram_gb":4,"requires_docker":true},"decision_summary":[{"label":"Requirements","value":"Min 4 GB RAM; Requires Docker; PortAudio system dependency required.; Requires Python 3.12 environment and virtual environments"},{"label":"Adopt for","value":"WhisperLive offers nearly real-time speech transcription based on OpenAI's Whisper model across multiple hardware-accelerated backends."}]}}