WhisperLive social preview
tts-stt4,339MIT

WhisperLive

A nearly-live implementation of OpenAI's Whisper.

Updated Oct 31, 2026
GitHub Docs
Platforms
macos, linux, docker, web
Pricing
free-open-source
Status
active
License
MIT

What it does

Core capabilities at a glance

  • Dictation
  • OBS
  • Openai
  • Openvino
  • Openvino Intel
  • Rocm
  • Tensorrt
  • Tensorrt LLM

Deep dive

The full breakdown - performance, comparisons, and setup

WhisperLive

WhisperLive is a speech (TTS/STT) tool - A nearly-live implementation of OpenAI's Whisper.

Overview

This project is a real-time transcription application that uses the OpenAI Whisper model to convert speech input into text output. It can be used to transcribe both live audio input from microphone and pre-recorded audio files.

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')

  • Please follow TensorRT_whisper readme for setup of NVIDIA/TensorRT-LLM and for building Whisper-TensorRT engine.

The server supports 3 backends 'faster_whisper', 'tensorrt' and 'openvino'. If running 'tensorrt' backend follow TensorRT_whisper readme

  • TensorRT backend. Currently, we recommend to only use the docker setup for TensorRT. Follow TensorRT_whisper readme which works as expected. Make sure to build your TensorRT Engines before running the server with TensorRT backend.

WhisperLive is open-source, written primarily in Python, with 4,339 GitHub stars under the MIT license. The latest release is v0.10.0 (2026-09-07).

Key capabilities

From the project's documentation:

  • Custom Vocabulary / Hotwords
  • Streaming Client (Manual Audio Chunking)
  • Whisper Live Server in Docker
  • Install PortAudio (required system dependency for microphone input via PyAudio)
  • Install 3.12 venv (on Fedora sudo dnf install -y python3.12 python3.12-pip)
  • Install whisper-live from pip

Install

A quick way to get started (always check the official docs for the latest):

pip install whisper-live

How it fits a local-AI stack

WhisperLive runs on your own hardware, so pair it with a model and a GPU sized to your needs. Use the VRAM calculator to pick a model that fits your card, and see what you can run for hardware guidance. Related speech (TTS/STT) tools in the directory:

Sources

Stats from GitHub, 2026-10-30.

Frequently asked

Quick answers to common questions

What is WhisperLive?

WhisperLive is a tts-stt tool for local AI workloads. A nearly-live implementation of OpenAI's Whisper.

Is WhisperLive free and open source?

Yes, WhisperLive has 4,339 GitHub stars and is licensed under MIT. You can self-host it for free on macos, linux, docker, web.

What platforms does WhisperLive support?

WhisperLive runs on macos, linux, docker, web.

What hardware do I need for WhisperLive?

The hardware requirements depend on which models you run. Check our hardware directory for compatible GPUs and systems. WhisperLive has 4,339 GitHub stars and an active community.

Does WhisperLive support GPU acceleration?

WhisperLive supports GPU acceleration via CUDA, Metal, or Vulkan depending on your platform. For the best performance, pair it with an NVIDIA RTX 4090 or 5090.

What are the best alternatives to WhisperLive?

Popular alternatives include other tts-stt tools in our directory. Browse our full collection at /tool for comparisons, community reviews, and benchmark data to find the right fit for your workflow.

How much does WhisperLive cost?

WhisperLive is free-open-source. It is completely free and open source to self-host.

Pairs well with

Complementary tools, models, and hardware