Voice

Speech in and out — text-to-speech, voice cloning and speech-to-text models and apps.

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.

voicelocal

→ alternative to pocket-tts, voicebox

Zackriya-Solutions 25.1k · 1 months ago

meetily

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.

localvoice

→ alternative to rowboat, Ollama

Open-LLM-VTuber 12.6k · 2 months ago

Open-LLM-VTuber

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

voice

→ pairs well with Ollama

kyutai-labs 7.6k · 23 days ago

pocket-tts

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.

localvoice

→ pairs well with Ollama, LuxTTS

jamiepine 41.7k · 3 days ago

voicebox

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.

voice

→ alternative to pocket-tts, LuxTTS