ArchestackGitHub ↗ (opens in a new tab)

Open-source alternatives to Wispr Flow

Voicebox leads with 74, ahead of openwhispr (72). Updated from public GitHub data.

The highest-scoring open-source projects in Voice. They are picks, not exact replacements, so read the weaknesses before you switch. The same picks fit if you are leaving WisprFlow or Superwhisper.

Open-source alternatives to Wispr Flow
RankProjectScore
1VoiceboxLocal voice studio for cloning, TTS, dictation and agent speechVoice59.2k starsMIT74 out of 100
2openwhisprCross-platform voice dictation and meeting transcription app with local or cloud modelsVoice10.5k starsMIT72 out of 100

Reviews

174 out of 100

Voicebox

Local voice studio for cloning, TTS, dictation and agent speech

59.2k starsMITlast commit Oct 2026

Its own README calls it an alternative to Wispr Flow.

Desktop app (Tauri) and Docker service that clones voices from a short sample and generates speech through eight TTS engines, including Qwen3-TTS, Chatterbox and Kokoro, in 23 languages. Adds Whisper dictation with a global hotkey, a REST API on port 17493 and an MCP server so coding agents can speak in a cloned voice. For individuals who want ElevenLabs-style voice I/O on their own machine.

Strengths

  • Eight switchable TTS engines; Chatterbox Multilingual covers 23 languages
  • REST API plus HTTP and stdio MCP server for Claude Code, Cursor, Windsurf
  • Runs on MLX, CUDA, ROCm, DirectML, Intel Arc or CPU
  • Auto-chunking with crossfade handles scripts up to 50,000 characters

Weaknesses

  • No prebuilt Linux binaries; build from source or use Docker
  • Only Chatterbox Turbo honors tags like [laugh]; other engines read them aloud
  • Dictation auto-paste and the permission flow are macOS-specific
  • Docker deployment gets one line in the README; details are in external docs
  • GPU optional
  • Docker + Compose
  • Models: Qwen3-TTS 0.6B/1.7B, Qwen CustomVoice, Qwen VoiceDesign, LuxTTS, Chatterbox Multilingual
  • port 17493
  • README: alternative to ElevenLabs, Wispr Flow
Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)
272 out of 100

openwhispr

Cross-platform voice dictation and meeting transcription app with local or cloud models

10.5k starsMITlast commit Oct 2026

Its own README calls it an alternative to Wispr Flow.

OpenWhispr is an Electron desktop app for macOS, Windows and Linux. A global hotkey records speech and pastes the transcript at the cursor, using local models (Whisper via whisper.cpp, NVIDIA Parakeet via sherpa-onnx) or cloud providers. It also covers meeting transcription with speaker diarization, notes with semantic search, and a voice assistant that talks to GPT, Claude, Gemini or local models.

Strengths

  • Offline transcription with Whisper and Parakeet; audio stays on the device
  • GPU-accelerated local Whisper on Metal, CUDA and Vulkan
  • Local speaker diarization and voice fingerprinting across meetings
  • Public API and MCP server for notes and transcriptions

Weaknesses

  • Intel Macs lack live speaker identification and semantic notes search
  • Cloud sync, sharing and team spaces depend on OpenWhispr Cloud
  • Source setup requires Node.js 24+; no Docker or server deployment
  • Enterprise SSO and SCIM controls are listed, with no edition details in the README
  • GPU optional
  • Needs Node.js 24+
  • Models: Whisper, NVIDIA Parakeet, Cohere Transcribe, llama.cpp local LLMs, OpenAI
  • README: alternative to Granola, Wispr Flow
Documentation ↗ (opens in a new tab)Website ↗ (opens in a new tab)Repository on GitHub ↗ (opens in a new tab)