Developer Tools●●Solid
Kitten TTS Based Low-Latency Streaming Voice Assistant on CPU
Sub-sentence TTS streaming beats Piper/Sherpa-ONNX latency by token-level triggering on CPU.
Niche GemWizardry
gauravvij137
303mo ago
Back to browse
GitHub Repository
🦆 Real time voice interface to talk to Claude Code
18 starsTypeScript
Duck Talk – Real-time voice interface to talk to your Claude Code
by DanyWin·Feb 26, 2026·6 points·0 comments
AI Analysis
●●SolidCozySolve My ProblemShip It
Claude Code talks back—low-latency voice I/O over generic agent wrapper.
Strengths
- •Streaming TTS (sentence-by-sentence) feels responsive vs waiting for full response completion.
- •Voice interrupt via 'stop' keyword gives real control in async workflows.
- •Zero agent modification; works as thin layer on top of any Live Speech model backend.
Weaknesses
- •Solves a narrow use case: voice coding assistants already exist (Superpowered Whisper, custom MCP voice tools).
- •Depends on Claude Code CLI and Gemini Live API availability; no fallback if either changes.
Category
Target Audience
Hands-free coding workflows, Claude Code users, accessibility-first developers.
Similar To
SuperWhisper · Wispr Flow · Wunderbucket
Similar Projects
Developer Tools●●Solid
I built a sub-500ms latency voice agent from scratch
Outperformed Vapi 2× on latency by treating voice as turn-taking, not transcription.
Big BrainWizardry
nicktikhonov
5701533mo ago
Hardware●●●Banger
Voice AI Toys on ESP32 with Cloudflare Durable Objects
Cloudflare Durable Objects + ESP32 creates global voice toy network.
WizardryNiche Gem
akadeb
201mo ago
Hardware●●●Banger
An open source rubber ducking robot, also a joke
Physical AI companion that approves Claude commands by voice instead of modal dialogs.
Crowd PleaserCozyShip It
jftesser
302mo ago
Hardware●●●Banger
An Open-Source Yoto Toy with Qwen3-TTS
Voice cloning on ESP32 without cloud beats Yoto's subscription model completely.
WizardryZero to OneDark Horse
akadeb
312mo ago
AI/ML●●Solid
Ava – AI Voice Agent for Traditional Phone Systems(Python+Asterisk/ARI)
Adds AI voice to legacy Asterisk systems without ripping out existing telephony.
Niche GemBig Brain
hkjarral
712mo ago