# Hugging Face — Hugging Face and Cerebras bring Gemma 4 to real-time voice AI

- Company: Hugging Face (huggingface.co)
- Announced: 2026-07-01T00:00:00+00:00
- Category: partnership-acquisition
- Subject: Platform
- Models affected: Gemma 4, Gemma 4 31B, Parakeet, Qwen3TTS
- Source: https://huggingface.co/blog/cerebras-gemma4-voice-ai
- Record: https://forck.live/items/1467-hugging-face-and-cerebras-bring-gemma-4-to-real-time-voice-ai

Hugging Face and Cerebras announce a real-time speech-to-speech pipeline using Google DeepMind's Gemma 4 VLM on Cerebras hardware for low-latency inference, with an open, modular architecture that includes Nvidia's Parakeet for speech recognition and Alibaba's Qwen3TTS for text-to-speech. The system is demonstrated in a demo and the code is available on GitHub. The collaboration aims to improve latency and naturalness in voice AI interactions.

## Evidence

Verbatim from https://huggingface.co/blog/cerebras-gemma4-voice-ai:

> Today, we demonstrate what becomes possible when an open, modular voice AI architecture is paired with industry-leading inference speed.

---

Record: https://forck.live/items/1467-hugging-face-and-cerebras-bring-gemma-4-to-real-time-voice-ai
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md