Sussurro – local, opensource, speech to text with system-wide dictation
Local Whisper + fine-tuned Qwen beats cloud STT on privacy, latency, cost.

Pay-as-you-go pricing doesn't beat AssemblyAI or Deepgram on infrastructure.
Web developers adding voice input to applications
AssemblyAI · Deepgram · Google Cloud Speech-to-Text
Local Whisper + fine-tuned Qwen beats cloud STT on privacy, latency, cost.
Four swap-able engines, 80ms latency, no subscription—beats Apple's 60-second timeout hard.
Fully-local Whisper+Ollama voice stack; real Windows app with emoji widget.
Replaces Whispr Flow and Monologue—fully open, local Whisper, any provider.
Offline voice typing for Linux—finally fills a gap Windows and macOS solved years ago.
Another voice cloning platform when ElevenLabs already dominates this space.