Fully Open-Source Real-Time Voice Digital Human Pipeline
victormustar · x · 2026-07-03
Developer victormustar shared a fully open-source real-time voice digital human pipeline: Silero VAD for voice activity detection, Parakeet for speech recognition, Gemma 4 31B (running on Cerebras for fast responses) for dialogue, and Qwen3-TTS for speech synthesis, transmitting PCM audio via native WebSocket. The digital human's avatar and lip-sync use the TalkingHead and HeadAudio projects. The entire solution is built exclusively on open models.
More from Infra
- DeepSpeed shows AutoEP/AutoTP/AutoSP parallelism gains, hosts office hours — PyTorch · 2026-10-27
- Cloudflare Durable Objects validated as top architecture for AI agent WebSocket servers — tristanbob · 2026-10-27
- Gary Marcus: With Q3 data added, Anthropic's compute-efficiency growth shows deceleration — GaryMarcus · 2026-10-27
- SpaceX locks in $40B GPU financing deal with Apollo, the largest ever committed — TechCrunch AI · 2026-10-27
- Inference is just Kubernetes with a multi-trillion-dollar market, and the communities overlap — matt_slotnick · 2026-10-27
- vLLM eyes Rust migration as inference engines race to rewrite the stack — AccBalanced · 2026-10-27