Developer Tools●Mid
Forking mods to add interactive mode
Useful mods fork with interactive mode, but maintaining a sunset tool is a shrinking audience.
CozyNiche Gem
playnext
202mo ago
Back to browse
GitHub Repository
Voice mode for Gemini CLI
21 starsTypeScript
Voice Mode for Gemini CLI Using the Live API
by kstonekuan·Mar 14, 2026·4 points·0 comments
AI Analysis
●●SolidShip ItNiche Gem
Rust audio capture with server-side VAD, but no push-to-talk yet.
Strengths
- •Native Rust addon with lock-free ring buffer for audio capture
- •Server-side voice activity detection eliminates local VAD complexity
- •Pre-built binaries mean no Rust toolchain needed for users
Weaknesses
- •Gemini CLI extension limits prevent push-to-talk and live waveform display
- •Requires native integration for full voice mode experience
Category
Target Audience
Developers using Gemini CLI who want voice input
Similar To
Claude Code voice mode · Superwhisper · Whisper CLI
Similar Projects
Productivity●Mid
AuraSpend " Voice-first expense tracker using Gemini for NLU
Voice-first expense entry with Gemini NLU, but expense tracking is solved by YNAB, Mint, Monarch.
Ship It
subhanzg
103mo ago
SaaS●●Solid
TypelessForm – Add voice input to any HTML form with one script tag
Turns any HTML form voice-accessible with one script, auto-mapping speech to fields.
SlickSolve My Problem
alex1sa
202mo ago
AI/ML●Mid
Audio-to-Video with LTX-2
Audio-to-video is solved by Runway, Synthesia, and D-ID; this adds no clear differentiation.
Crowd PleaserEye Candy
runshouse
2323mo ago
Productivity●●Solid
Real-time voice-to-voice translation for any app on macOS
System-wide audio translation on macOS without cloud dependency.
Solve My ProblemSlick
kamban
102mo ago
AI/ML●●Solid
Parlor Jarvis – Realtime AI (audio+screen in, voice out) & multilingual
Multilingual local AI with screen sharing beats Parlor's English-only camera input.
Niche GemShip It
unusual_typo
821mo ago