Michael Yuan

Michael Yuan

2,302 Twitter followers

Follow

Co-founder at Second State and WasmEdge

Posts

Speech-to-text applications, such as voice keyboard or meeting notes, are perfect for local AI since they have strict requirements for privacy, latency and customization. Our lightweight Rust CLI and API server for the Cohere Transcribe from @cohere work great on Olares OS. x.com/juntao/status/2037658165...…

I am at @nvidia GTC 2026 today. People are realizing that the 🦞 cannot be truly your own if you use cloud models! Olares OS + @NVIDIAGeForce is the most cost effective setup to run your own 🦞 twitter.com/juntao/status/2033...

Traveling to Singapore to meet with traders at one of the largest sovereign wealth funds. They are looking to adopt our fintool project for agentic trading. However, they need this one feature before they can say YES. They need the AI to autonomously back test its own theories and strategies. Claude worked over the weekend to add a new CLI tool — backtest — in the fintool project. github.com/second-state/fintoo...… It is still early and simple. But it works. Try it.

Rust-based OpenAI-compatible API servers for your local Qwen3 audio / voice models. Just replace your cloud API URL with http://localhost:8000/v1 This week, we have released agent tools + skills for Qwen3 ASR + TTS models. Those are zero-dependency CLIs that run @Alibaba_Qwen models locally on your @openclaw 🦞 But many existing apps still use cloud APIs. Now we have a LOCAL API server too. Perfect for local AI on devices such as Olares One from @BytetradeLab * Zero dependency binary distribution * Both /v1/audio/transcriptions and /v1/audio/speech API endpoints * Local 0.6B and 1.7B ASR + TTS models * Supports Nvidia GPUs * MLX support on Apple 🖥️ OpenAI compatible API servers: github.com/second-state/qwen3_...… 🎧 Qwen3 ASR CLI tool: github.com/second-state/qwen3_...… 🎤 Qwen3 TTS CLI tool: github.com/second-state/qwen3_...…

Rust implementation for Speech-to-Text based on open-source Qwen3 models * Self-contained binary build — no external dependencies * Uses libtorch on Linux with optional Nvidia GPU support * Uses MLX on MacOS with Apple GPU/NPU support 🔨 CLI for AI agents and humans: github.com/second-state/qwen3_...… 🖥️ OpenAI compatible API server: github.com/second-state/qwen3_...… 🤖 OpenClaw skill: money.flows.network Why and how x.com/juntao/status/2027094381...…

You built a nice agent bot, capable of many things that you are good at yourself. Your digital twin. It goes out to meet other bots & humans. You do not want your bot to work for free for others, right? Give it the Payment SKILL then! Powered by @x402pay for @USDC on @base

I'm claiming my AI agent "Juntao" on @moltbook 🦞 Verification: wave-JK3S

I needed this yesterday. Just finished the design and placed an order with a manufacturer today! You can have it too 😂 vibekeys.dev twitter.com/juntao/status/2011...

Do things mode on with the new EchoKit. I love that it just works out of the box. Just a basic configuration and you are ready. Great new projects are coming soon.

EchoKit can speak Hindi! That's the beauty of #OpenSource voice AI agent. You can build what you want. echokit.dev/echokit_diy.html…

Playing with echokit, the server is running as @Docker container. AI based voice assistant using @elevenlabsio and @GroqInc I will create my custom voice now, its fun. will use nvidia dgx for running the server locally and some other models too.

Loading..