We are open-sourcing TTSKit! Run state-of-the-art text-to-speech models on... your Mac and iPhone. The launch version supports Qwen Qwen3-TTS and generates audio faster than real-time playback with sub-200 ms time-to-first-byte. Voice cloning and advanced speed optimizations will be in the next version. Link to the GitHub repo and models on Hugging Face in comments.show more

Playing with Qwen3-TTS is and MLX-Audio locally on Mac... Studio M3 Ultra 🔥 Amazing model by Qwen and great work by Prince Canuma bringing this magic to MLX! Tuning the voice with instructions feels like magic! Command and prompts to run it are in the video.show more

The speech on the FREE open source Sesame text... to speech is astonishing. It just killed Google’s voice project for podcasts and the monetization they hoped for. Here is a Hugging Face Gradio link to test: But download it and clone your voice!show more

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech... model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.show more

Also, you can now add the ability to talk... to your agents. Cloudflare /voice adds real-time voice to the Agents SDK. ~30 lines of server code to get started, with built-in speech to text and text to speech on Workers AI.show more

Qwen 3.6 models are now 2.5x times faster on... Atomic Chat with new MTP speedups. > MTP drafts several tokens ahead and verifies them in one pass. The speedup depends on the memory moved per pass. Users can run Qwen 3.6 models locally via the open-source Atomic Chat to test them!show more

“Bro spent all his XP points on strength and... 0 on speed.” I’m releasing my next book $100M Money Models. The launch is going to be something not soon forgotten. Link in comments + hilarious replies.show more

Inspired by Andrej Karpathy and the idea of using... games to compare LLMs, I've built a version of the game Codenames where different models are paired in teams to play the game with each other. Fun to see o3-mini team with R1 against Grok and Gemini! Link and repo below.show more

parakeet.cpp: native C++/ggml (ggml) inference for NVIDIA AI Developer's... Parakeet, one of the best speech-to-text models out there, from the LocalAI team. Every Parakeet model (TDT/CTC/RNNT/hybrid + cache-aware streaming), byte-for-byte identical output to NeMo, now running anywhere with no Python and even a bit faster, on CPU and GPU. Quantized GGUF on Hugging Face 🤗 Huge thanks to Georgi Gerganov for ggml and to NVIDIA AI Developer for releasing Parakeet! 🧵show more

You don't need a GPU for fast studio grade... voice cloning anymore. Qwen3 TTS (1.7B Q4_K_M) + mainline llama.cpp is officially the fastest way to generate zero shot voice clones using 100% pure CPU execution. Following up on my last post where we ran the Q8 model on a GPU, we just took local C++ voice synthesis a massive step further. The open source community quantized Alibaba's SOTA Qwen3 TTS model down to Q4_K_M GGUF, completely freeing local audio pipelines from dedicated graphics hardware. Here is the real world benchmark and hardware breakdown of running SOTA voice cloning on CPU: # Architecture & Model Setup Using Qwen3-TTS-12Hz-1.7B-Base-Q4_K_M.gguf paired with the 8 bit multimodal projector (mmproj-Q8_0.gguf), llama.cpp executes the entire pipeline in pure C++. No PyTorch, no CUDA dependencies, and no VRAM bottlenecks. # Real-World Memory Footprint - Baseline RAM: 1.6 GB system idle. - Peak Generation RAM: 8 GB RAM during active voice synthesis. - Requirement: Any basic machine with at least 8 GB of system RAM can run this easily. # Real World CPU Benchmarks - Google Colab Free Tier (Throttled 2 Core CPU): Synthesizes a 5 sec studio quality audio clip (~8 words) in 45 seconds. - Modern Consumer CPU (Intel i5/i7 13th/14th Gen or AMD Ryzen 7000/9000): generation should drop to 5 to 20 seconds (nearly 1:1 real-time generation speed!). # Zero Shot Voice Cloning Quality Pass any 5 to 20 second .wav audio sample to the C++ engine using the --tts-speaker-file flag. It yields clean, natural sounding cloned speech with virtually zero quality loss compared to unquantized FP16 weights. To make testing seamless, I built an updated zero config Google Colab notebook. It pulls the official pre built llama.cpp CPU binaries (zero compilation time!) launches a live Gradio web app right in your browser. Record a 5 second clip from your mic (or drop a .mp3, .wav file), type text, and generate cloned audio on CPU. Native C++ audio models are making edge based, offline AI voice agents a reality. Links to the free Q4 CPU Colab notebook and the Q4_K_M GGUF HuggingFace repository are in the replies below! Which models have you been running on your CPUs? What CPU hardware are you using for local inference?show more

Each booth at Apsara 2025 is buzzing with the... latest AI innovations! From the next-generation large language models of the Qwen3 family and the Wan 2.5 models to the new agent development framework feature in Model Studio, the updates are rolling in! Stay tuned as we zoom into the booths and bring the breakthroughs to you!🔥show more

Use Your Private Models on Comfy Cloud! Continue client... work safely — or generate with your experimental private models. You can now import models directly from private Hugging Face or Civitai repos. Just add your private key and model URL, and we will bring the models to your workflow! Everything you import stays 100% private to your account.show more

Meet Stable Audio 3.0, the open-weight model family built... for artistic experimentation. This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built. The 4-1-1 on 3.0: 📣 You own your outputs, and can distribute and commercialize them under the Stability AI Community License (up to $1 million in revenue). 🎵 New and improved capabilities include variable-length generation up to six minutes, and full song composition on portable devices, no GPU required. ✅ Trained on a fully licensed dataset. 🎨 You can customize the models on your own library with support for LoRa training, which we’ve documented for the first time. More on the models 👇show more

We've just hit 1M open datasets on the Hugging... Face Hub 🎉 Open models need open data. Today we hit that milestone, together with the most incredible community in AI! 🤗 Onwards to the next million 🚀show more

MiniMax Audio just leveled up with the new Speech-02... model! Turn any file or URL into lifelike audio instantly. Create audiobooks and podcasts effortlessly with up to 200k-character in a single input. Enjoy ultra-realistic TTS in 30+ languages with native flair, unlimited voice cloning, and sub-second streaming! Here are 4 examples:show more

⏱️ THE WAIT IS FINALLY OVER In just 2... days you will see what FAR Labs have been building. We are about to reveal the foundation of FAR AI, built on new compute, new biometric signals, new science models, and new forms of intelligent play. Each part is designed to help you run faster, produce more, and open fresh revenue streams across AI, science, and gaming. You will see how these layers connect and how they create a system built for real users, real ownership, and real outcomes. Be the first to use FAR AI and unlock new revenue. Follow these steps: 1. Click the link below. 2. Enter your email in the box. 3. Confirm your signup and you are in. Here's the link 👉 PS Spots for early access will move fast, act now.show more

llama.cpp isn't just for text LLMs anymore. Pure C++... zero shot voice cloning just officially landed in mainline. Text generation was only step one. If you’re building autonomous local AI agents, real time voice assistants, or edge workflows, instant low latency audio is the missing piece. Thanks to PR #26254, Alibaba’s state of the art Qwen3 TTS model family is now natively supported directly inside the llama.cpp repository under the multimodal (mtmd) framework. No Python bloat. No massive PyTorch CUDA overhead. Just raw, hyper optimized C++ running GGUF voice weights. Here is why this native update is a massive deal for the open source local AI stack: # Multimodal Architecture (.gguf + mmproj) Qwen3-TTS splits the workload between the base language model backbone and a multimodal projection adapter. llama.cpp handles this using the llama-tts binary, mapping the text model alongside its --mmproj projector to process audio tokens seamlessly. # Zero Shot Voice Cloning in Seconds You don't need fine tuning or massive dataset training. Feed the C++ engine a single 5 to 10 second .wav audio sample using the --tts-speaker-file flag, and it accurately clones the exact timbre, tone, and accent on the fly. # Real World T4 GPU Benchmark & Resource FootprintRunning the 1.7B Base model in 8-bit quantization (Q8_0): - VRAM Footprint: ~7 GB peak VRAM during active zero-shot cloning. - Audio Quality: Studio grade, natural-sounding voice output in seconds. • - Execution: Direct execution via native compiled binaries or sub process calls. # Coming Next to llama-server (PR #26603) Beyond CLI execution, a native POST /tts HTTP endpoint is currently being added to llama-server, which will soon allow you to trigger voice generation directly via standard REST API requests! # quick note on Colab compilation: Because this code was merged into mainline very recently, pre-built third-party binaries haven't fully caught up yet. Compiling llama-tts directly from source on Google Colab's free CPU instance can take about 1 hour (or ~1-2 minutes if targeting single GPU arch like -DCMAKE_CUDA_ARCHITECTURES=75). Be patient during the build step, or compile it locally on your own rig for instant execution! To test this out yourself, I built a zero config Google Colab notebook that compiles llama.cpp, downloads the Q8_0 GGUF files from HuggingFace, and spins up an interactive Gradio Studio UI so you can record/upload 3 second clips and clone voices in real time. Stop sleeping on native C++ audio. The era of bulky Python audio pipelines is officially over. Links to the free Google Colab notebook and the official ggml org GGUF HuggingFace model repository are in the replies below! available in q4 and q8 both variants, 1 GB and 1.85 GBs respectively (requires additional ~500MB mmproj gguf) Are you building local voice agents yet? What does your current audio stack look like? Drop your setups below!show more

Today, we're shipping MLX support for TADA, our open-source... text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.show more

In the next update we will add a voting... feature to our staking platform We are planning to launch the first voting on Sunday and invite XRPL projects to take part in it. 📢Tag project with the strongest community and we will invite them to vote! (1/2)⬇️show more