--- title: "Fun Audio Chat 8B: This SPEECH TO SPEECH Open Model is ACTUALLY AMAZING!" url: https://daily.dev/posts/fun-audio-chat-8b-this-speech-to-speech-open-model-is-actually-amazing--8qz5amvfc source_url: https://www.youtube.com/watch?v=Rvi949f9tyU type: video:youtube source: "AICodeKing" published: 2026-02-01T09:25:29.533Z updated: 2026-02-01T11:12:34.721Z reading_time: 11 upvotes: 0 comments: 0 language: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Fun Audio Chat 8B: This SPEECH TO SPEECH Open Model is ACTUALLY AMAZING! **[AICodeKing](https://daily.dev/sources/aicodeking)** · 11 min read · 0 upvotes · 0 comments ## Summary In this video, I explore Alibaba's new Fun Audio Chat, a powerful Large Audio Language Model designed for natural, low-latency voice conversations. Unlike cloud-based options like Gemini Live, this fully open-source model runs locally on your hardware. I'll break down its unique architecture, features like voice empathy and function calling, and show you exactly how to set it up. -- Resources: GitHub: https://github.com/FunAudioLLM/Fun-Audio-Chat HuggingFace: https://huggingface.co/FunAudioLLM/Fun-Audio-Chat-8B ModelScope: https://modelscope.cn/FunAudioLLM/Fun-Audio-Chat-8B Demo Page: https://funaudiollm.github.io/funaudiochat -- Key Takeaways: 🗣️ Fun Audio Chat is an open-source Large Audio Language Model (LALM) built for real-time, low-latency voice interaction. ⚡ A unique dual-resolution architecture (5Hz/25Hz) reduces GPU usage by 50% while maintaining high output quality. 🎭 The model features voice empathy, detecting emotional context like tone and pace to respond with appropriate energy. 🛠️ Supports advanced capabilities including speech instruction-following, function calling, and general audio understanding. 🔄 Full-duplex interaction allows you to interrupt the model mid-sentence for natural turn-taking. 📈 It ranks top-tier on major benchmarks like OpenAudioBench, VoiceBench, and MMAU. 🖥️ You can run this locally with Python 3.12 and a GPU with 24GB VRAM (like an RTX 3090 or 4090). ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [Don’t just attend KubeCon \+ CloudNativeCon, Merge Forward your experience\!](https://daily.dev/posts/don-t-just-attend-kubecon-cloudnativecon-merge-forward-your-experience--l0rpp73x8) · CNCF · 0 upvotes · 0 comments - [Announcing H2 2026 KCDs](https://daily.dev/posts/announcing-h2-2026-kcds-m96goajm1) · CNCF · 1 upvotes · 0 comments - [Two months of Open Community Groups](https://daily.dev/posts/two-months-of-open-community-groups-asf52zhbs) · CNCF · 0 upvotes · 0 comments --- [View this post on daily.dev](https://daily.dev/posts/fun-audio-chat-8b-this-speech-to-speech-open-model-is-actually-amazing--8qz5amvfc)