Which AI models does the pipeline use?

The pipeline uses Nvidia's Parakeet for speech recognition, Google DeepMind's Gemma 4 31B as the language model (running on Cerebras inference), and Alibaba's Qwen3TTS for text-to-speech conversion.

Where is this technology already deployed?

The Hugging Face speech-to-speech pipeline already powers Reachy Mini robots, with more than 9,000 robots in the wild.

Open-Source AIAudio & SpeechHugging Face BlogJul 1, 2026Jul 2, 2026, 01:00 JST1 min read

Hugging Face and Cerebras demo real-time voice AI with low latency

Send on LINE

Key takeaway

Hugging Face and Cerebras have demonstrated a real-time speech-to-speech AI system that delivers natural, low-latency conversations by combining open-source models with fast inference.
The system solves a critical problem in voice AI: production systems often experience multi-second delays that make interactions feel unreliable, but this architecture delivers stable, responsive performance at the long tail.
The pipeline is already powering over 9,000 Reachy Mini robots and is fully open, allowing developers to modify and extend it for different applications.

3 Key Points

What happened
Hugging Face and Cerebras demonstrated a speech-to-speech AI pipeline that combines open-source models—Nvidia's Parakeet for speech recognition, Google DeepMind's Gemma 4 31B language model running on Cerebras inference, and Alibaba's Qwen3TTS for text-to-speech—to enable natural, fast conversational responses. The modular, open architecture allows developers to inspect, modify, and extend each component.
Why it matters
Latency has been a major bottleneck in voice AI systems; many production systems experience multi-second delays at the P95 (worst-case scenarios), making conversations feel unreliable and unnatural. By making language-model inference dramatically faster and more stable, Cerebras addresses this bottleneck. For robots, voice assistants, and embodied AI, this responsiveness is not a cosmetic improvement—it makes interactions feel alive and natural at scale, which may enable more practical deployment of conversational AI in real-world applications.
What to watch
The pipeline already powers Reachy Mini robots, with more than 9,000 robots in the wild. Developers can explore the demo on Hugging Face Space and the code in the huggingface/speech-to-speech repository.

Ask the AI about this article →

Summaries like this, in your inbox every morning.

Get news like this every morning — free

FAQ

Which AI models does the pipeline use?: The pipeline uses Nvidia's Parakeet for speech recognition, Google DeepMind's Gemma 4 31B as the language model (running on Cerebras inference), and Alibaba's Qwen3TTS for text-to-speech conversion.
Where is this technology already deployed?: The Hugging Face speech-to-speech pipeline already powers Reachy Mini robots, with more than 9,000 robots in the wild.

Hugging Face BlogRead Original Article

Send on LINE

Get the latest Open-Source AI news every morning

For example, today's edition would include:

Z.ai runs GLM on 100,000 Chinese AI chipsDIGITIMES Asia · 2h ago
Broadcom Unveils VMware AI Factory for Faster Private AITop Companies AI · 12h ago
OpenClaw 2.0 launches with major updateSiliconANGLE AI · 17h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Subscribe free →

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →