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
- Intel 10-Q points to 18A/14A progress and “potential significant external customers” — BenBajarin · 2026-07-27
- Moonshot’s Kimi K3 lands on Together with reserved throughput and 65% lower cost — togethercompute · 2026-07-27
- OpenAI may be hitting compute limits as Codex and ChatGPT Work jump from 2M to 10M users — JoshuaJBouw · 2026-07-27
- NVIDIA says Vera CPU is speeding up next-gen CPU and GPU design cycles — nordicinst · 2026-07-27
- NVIDIA says Nemotron 3 Ultra hit 97.1% on agentic RTL chip-design tasks — NVIDIAAI · 2026-07-27
- NVIDIA says Vera CPU lifted selected EDA workloads by up to 1.5x — NVIDIA Blog · 2026-07-27