Voice

PunithVT 534 · 27 days ago

Self-hosted digital human: a photo plus 10s of voice becomes a real-time talking head — Whisper to LLM to Chatterbox TTS to MuseTalk lip-sync, streamed over WebSocket, with barge-in.

video-db 1.6k · 1 months ago

Meetings as live agent loops: local recording, dual-channel you-vs-them transcription, in-call AI suggestions, auto-triggered MCP tools mid-conversation, and post-call summaries. macOS/Windows.

cjpais 33.8k · today

Push-to-talk offline dictation: hotkey, speak, text lands in whatever field has focus. Whisper or Parakeet fully on-device; cross-platform Rust/Tauri, built to be forked.

ysharma3501 5.5k · 4 months ago

Lightweight voice-cloning TTS — 48kHz speech at 150x realtime, fits in 1GB VRAM and runs on CPU or MPS. SOTA cloning from a ~3s reference sample, rivaling models 10x larger.

Zackriya-Solutions 31.8k · 1 months ago

Privacy-first meeting note-taker that runs 100% on-device: live Whisper/Parakeet transcription, speaker diarization, local Ollama summaries. Desktop app for macOS & Windows — no cloud, no call bots.

Open-LLM-VTuber 14.1k · 5 months ago

Hands-free voice conversation with any LLM behind a Live2D animated face — voice interruption included, running fully local and cross-platform.

kyutai-labs 9.9k · yesterday

Kyutai's 100M-parameter CPU-only TTS — streaming audio in ~200ms, ~6× real-time on two laptop cores, voice cloning, six languages. pip install and it talks.

huggingface 13.5k · yesterday

Modular local voice-agent pipeline — VAD→STT→LLM→TTS behind an OpenAI Realtime-compatible WebSocket; every stage swappable, the LLM slot takes any OpenAI-compatible server. Powers Reachy Mini robots.

jamiepine 57.5k · 8 days ago

Local-first AI voice studio: clone voices, generate speech via 7 TTS engines in 23 languages, dictate system-wide with Whisper, and give any MCP-aware agent a cloned voice. Tauri, MLX/CUDA.

xybrid-ai 478 · today

Cross-platform on-device AI toolkit: run LLMs, ASR and TTS natively from Flutter, Unity, Kotlin, Swift or Rust on a llama.cpp and ONNX Runtime core. Private, offline, no cloud.