Hugging Face 联手 Cerebras 推 Gemma 4 实时语音 AI

原标题:Hugging Face and Cerebras bring Gemma 4 to real-time voice AI
68AI 研判分

Hugging Face 与 Cerebras 合作,将 Gemma 4 模型集成至低延迟推理平台,打造开源模块化实时语音交互架构。该方案通过级联式语音处理显著降低响应时间,旨在解决当前语音 AI 中用户体验受限于延迟的核心痛点。

报道正文

本文目录8 个章节

返回文章列表

Hugging Face 与 Cerebras 将 Gemma 4 引入实时语音 AI

发布于 2026 年 7 月 1 日 在 GitHub 上更新 点赞 107

Amir Mahla A-Mahla Andres Marafioti andito Leandro von Werra lvwerra Saurabh Vyas vyassaurabh cerebras

对于语音 AI 而言,延迟是一个关键参数。开发者们在模型质量方面取得了巨大进步,但用户体验仍常常受限于响应时间。Hugging Face 和 Cerebras 正在改变这一体验。今天,我们展示了当开放、模块化的语音 AI 架构与行业领先的推理速度相结合时,所能实现的可能性。

其结果是一种感觉更加自然的语音到语音(speech-to-speech)体验。用户无需等待 AI 回应,对话便能以人们期望的人类交互般的响应速度流畅进行。

架构:一个开放、级联的语音到语音技术栈

该演示构建为一个实时的语音到语音 pipeline。系统的每个部分都是模块化、开放且可替换的,使开发者能够轻松地将该技术栈适配于不同的助手、机器人、产品或研究项目。

这创建了一个完全开放的语音到语音闭环:

TEXT
Speech input
  -> speech recognition with Nvidia's Parakeet
  -> Gemma 4 VLM inference on Cerebras
  -> text-to-speech with Alibaba's Qwen3TTS
  -> spoken response

该架构汇聚了开源 AI 生态系统的优势:Cerebras 提供快速推理,Google DeepMind 的 Gemma 4 31B 作为语言模型,Qwen 负责文本转语音。每一层都可以由开发者进行检查、修改和扩展。

Cerebras 与 Hugging Face 的合作关系

如今,一些生产系统虽然拥有合理的中位延迟,但在 P95 百分位上仍会经历令人沮丧的多秒延迟。当工具调用或多模态步骤需要多轮交互时,这些延迟变得更加明显。

Cerebras 有助于解决该技术栈中最重要的瓶颈之一:语言模型的响应时间。通过使推理显著更快且更稳定,Cerebras 让 Hugging Face pipeline 的其他部分得以充分发挥潜力。

That stability is especially important at the long tail. Many systems can deliver acceptable median response times, but occasional slow responses still make conversations feel unreliable.

Built for real-world interaction

This same Hugging Face speech-to-speech pipeline already powers Reachy Mini robots, with more than 9,000 robots in the wild. For robots, voice assistants, and embodied AI, responsiveness is not a cosmetic improvement. It is what makes the interaction feel alive.

The motivation to use Cerebras is therefore not simply cost reduction. It is low latency, predictable performance, and the ability to create real-time experiences that feel natural at scale.

This collaboration reflects a shared belief that the future of AI will be both open and performant. Open-source models, open infrastructure, and breakthrough inference speed together create a foundation for the next generation of conversational AI.

We invite developers to explore the demo, experiment with the code, and help shape what comes next for real-time voice AI.

Demo: Hugging Face Space

Repository: huggingface/speech-to-speech

Spaces mentioned in this article 1

More Articles from our Blog

[

llmsinference-providersbaseten

Baseten on Hugging Face Inference Providers 🔥

  • +4

36 August 6, 2026](https://huggingface.co/blog/baseten)[![](https://huggingface.co/blog/assets/skypilot-hf-storage/thumbnail.png)

guidepartnershipsopen-source-collab

Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot

  • +1

35 July 7, 2026](https://huggingface.co/blog/skypilot-hf-storage)

Community

RemiFabre Jul 1

We even crossed 10k Reachy Minis in the wild 😄

taniyahunter Jul 2

It's exciting to see how Hugging Face and Cerebras are pushing real-time voice technology forward. Fast responses make conversations feel much more comfortable and engaging, and that's exactly what users have been hoping for. 😊 When the delay is reduced, interactions become smoother and more natural, making voice experiences feel less like talking to software and more like having a real conversation.

What I appreciate most is the focus on an open and modular approach. That gives developers more flexibility to build solutions that fit different needs instead of being locked into a single ecosystem. The combination of strong model quality with impressive inference speed could help unlock many practical applications across education, customer support, accessibility, and beyond. 🚀

The emphasis on latency is absolutely the right direction because speed directly shapes the overall experience. Even the smartest system can feel frustrating if every response takes too long. Bringing that waiting time down creates a much more fluid interaction, and it's great to see innovation focused on something users notice immediately. 👏

Looking forward to seeing how this evolves over the coming months... Faster conversations... Better responsiveness... More natural interactions... Exciting progress for developers and users alike... 🌟🙂

saqib98 Jul 4 • edited Jul 4 saqib98 Jul 4 No description provided. xdenser Sep 1

Does anybody work on multipoint speech2speech interaction? I.e. when 2 or more people are talking to AI? I think LLM can handle messages from several persons when they are properly tagged. How about speech2text models - are there any works in this direction? The model would have to have some context and probably stereo audio input or some additional tagging to differentiate between persons. As an example practical usage: voice assistant in car, when we have more than one person there, not unusual. Also some public kiosks where a group of people can interact by voice. There is much more in it then just text tagging by voice, as in this case people could also talk to each other (not to AI) and here also some capturing of non-verbal communication will be needed.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here. Tap or paste here to upload images

· Sign up or log in to comment