Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Introducing Moonshine Web: real-time speech recognition running 100% locally in your browser! ๐Ÿš€ Faster and more accurate than Whisper ๐Ÿ”’ Privacy-focused (no data leaves your device) โšก๏ธ WebGPU accelerated (w/ WASM fallback) ๐Ÿ”ฅ Powered by ONNX Runtime Web and Transformers.js

xenovacom's profile picture

Xenova

16,019 subscribers

27,878 Aufrufe โ€ข vor 1 Jahr โ€ขvia X (Twitter)

BildungWissenschaft & Technologie
LIVE

Anya Rossiโ€ข Live Now

Private livecam show

11 Kommentare

Profilbild von Xenova
Xenovavor 1 Jahr

Huge shout-out to the Useful Sensors team for such an amazing model and to @waelyasmina for his 3D audio visualizer tutorial! ๐Ÿค— ๐Ÿง‘โ€๐Ÿ’ป Source code: ๐Ÿ”— Online demo:

Profilbild von AssemblyAI
AssemblyAIvor 1 Jahr

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates ๐Ÿ‘‡

Profilbild von mr.niko.la
mr.niko.lavor 1 Jahr

How does it compare to whisper v3 L wrt speed ?

Profilbild von Eyal ๐Ÿ
Eyal ๐Ÿvor 1 Jahr

The one man army strikes again!

Profilbild von Sean Aguinaga
Sean Aguinagavor 1 Jahr

โค๏ธ

Profilbild von Alex Volkov (Thursd/AI)
Alex Volkov (Thursd/AI)vor 1 Jahr

well damn

Profilbild von Vlad
Vladvor 1 Jahr

say what??? I will be testing this to see if i can add it to voice notes for what I'm building right now. Great work!

Profilbild von omid
omidvor 1 Jahr

This is cool

Profilbild von Addy Osmani
Addy Osmanivor 1 Jahr

This looks so good. Is Moonshine Base multilingual or English? Using Whisper w/TF and will have to play with this.

Profilbild von Xenova
Xenovavor 1 Jahr

The current generation of Moonshine models are English-only, but maybe the Useful Sensors team is planning on a multilingual model in future? ๐Ÿ˜ @keveman

Profilbild von Ivan Fioravanti แฏ…
Ivan Fioravanti แฏ…vor 1 Jahr

WOW! Really cool!

ร„hnliche Videos

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by ๐Ÿค— Transformers.js and onnxruntime-web! ๐Ÿ”’ On-device inference: no data sent to a server โšก๏ธ WebGPU-accelerated (> 20 t/s) ๐Ÿ“ฅ Model downloaded once and cached Try it out! ๐Ÿ‘‡
1:26

Introducing Phi-3 WebGPU, a private and powerful AI chatbot that runs locally in your browser, powered by ๐Ÿค— Transformers.js and onnxruntime-web! ๐Ÿ”’ On-device inference: no data sent to a server โšก๏ธ WebGPU-accelerated (> 20 t/s) ๐Ÿ“ฅ Model downloaded once and cached Try it out! ๐Ÿ‘‡

Xenova

117,684 Aufrufe โ€ข vor 2 Jahren

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! ๐Ÿคฏ The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! ๐Ÿ”ฅ Check out the demo (+ source code)! ๐Ÿ‘‡
0:25

It's finally possible: real-time in-browser speech recognition with OpenAI Whisper! ๐Ÿคฏ The model runs fully on-device using Transformers.js and ONNX Runtime Web, and supports multilingual transcription across 100 different languages! ๐Ÿ”ฅ Check out the demo (+ source code)! ๐Ÿ‘‡

Xenova

262,755 Aufrufe โ€ข vor 2 Jahren

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! ๐Ÿ”ฅ High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.๐Ÿค— Try it out yourself! Demo + source code below ๐Ÿ‘‡
0:32

Introducing TTS WebGPU: The first ever text-to-speech web app built with WebGPU acceleration! ๐Ÿ”ฅ High-quality and natural speech generation that runs 100% locally in your browser, powered by OuteTTS and Transformers.js.๐Ÿค— Try it out yourself! Demo + source code below ๐Ÿ‘‡

Xenova

19,666 Aufrufe โ€ข vor 1 Jahr

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible โ€” but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.
1:23

Behold... GPT-OSS (20B) running 100% locally in your browser on WebGPU. This shouldn't be possible โ€” but with Transformers.js v4 and ONNX Runtime Web, it is! A new class of AI apps is emerging. Zero-install, infinite distribution. Simply visit a website and run models locally.

Xenova

311,512 Aufrufe โ€ข vor 4 Monaten

NEW: Real-time conversational AI models can now run 100% locally in your browser! ๐Ÿคฏ ๐Ÿ” Privacy by design (no data leaves your device) ๐Ÿ’ฐ Completely free... forever ๐Ÿ“ฆ Zero installation required, just visit a website โšก๏ธ Blazingly-fast WebGPU-accelerated inference Try it out! ๐Ÿ‘‡
0:58

NEW: Real-time conversational AI models can now run 100% locally in your browser! ๐Ÿคฏ ๐Ÿ” Privacy by design (no data leaves your device) ๐Ÿ’ฐ Completely free... forever ๐Ÿ“ฆ Zero installation required, just visit a website โšก๏ธ Blazingly-fast WebGPU-accelerated inference Try it out! ๐Ÿ‘‡

Xenova

12,094 Aufrufe โ€ข vor 1 Jahr

Woah... This is the fastest Transformers.js has ever been! ๐Ÿคฏ Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! ๐Ÿš€ No server required. โšก๏ธ WebGPU-accelerated in-browser inference ๐Ÿ“ฆ Optimized ONNX exports w/ GQA ๐Ÿ’ฌ Multi-round conversations w/ KV caching
0:20

Woah... This is the fastest Transformers.js has ever been! ๐Ÿคฏ Run a 1.7B LLM 100% locally in your browser at over 130 tokens per second! ๐Ÿš€ No server required. โšก๏ธ WebGPU-accelerated in-browser inference ๐Ÿ“ฆ Optimized ONNX exports w/ GQA ๐Ÿ’ฌ Multi-round conversations w/ KV caching

Xenova

54,099 Aufrufe โ€ข vor 1 Jahr

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by ๐Ÿค— Transformers.js. WebGPU support coming soon! ๐Ÿ‘‰ npm i kokoro-js ๐Ÿ‘ˆ Link to demo (+ sample code) in ๐Ÿงต
0:43

Introducing Kokoro.js, a new JavaScript library for running Kokoro TTS, an 82 million parameter text-to-speech model, 100% locally in the browser w/ WASM. Powered by ๐Ÿค— Transformers.js. WebGPU support coming soon! ๐Ÿ‘‰ npm i kokoro-js ๐Ÿ‘ˆ Link to demo (+ sample code) in ๐Ÿงต

Xenova

40,340 Aufrufe โ€ข vor 1 Jahr

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! ๐Ÿคฏ Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web
0:45

Okay, this is actually insane... You can now run LFM2.5-1.2B-Thinking (a 1.2B parameter LLM from @LiquidAI) at over 200 tokens per second directly in your browser on WebGPU! ๐Ÿคฏ Zero install. Fully private. Blazingly fast. Powered by Transformers.js and ONNX Runtime Web

Xenova

103,001 Aufrufe โ€ข vor 4 Monaten

Introducing SmolVLM 256M (& 500M): The worldโ€™s smallest multimodal model. Designed for efficiency and perfect for on-device applications! ๐Ÿ”ฅ Itโ€™s so small, it can even run 100% locally in your browser on WebGPU! ๐Ÿค Powered by Transformers.js! โšก๏ธ Try it out yourself! ๐Ÿ‘‡
0:26

Introducing SmolVLM 256M (& 500M): The worldโ€™s smallest multimodal model. Designed for efficiency and perfect for on-device applications! ๐Ÿ”ฅ Itโ€™s so small, it can even run 100% locally in your browser on WebGPU! ๐Ÿค Powered by Transformers.js! โšก๏ธ Try it out yourself! ๐Ÿ‘‡

Xenova

24,966 Aufrufe โ€ข vor 1 Jahr

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! ๐Ÿคฏ This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! ๐Ÿ˜ Who's building this?
0:22

Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! ๐Ÿคฏ This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! ๐Ÿ˜ Who's building this?

Xenova

42,882 Aufrufe โ€ข vor 10 Monaten

Introducing Whisper Timestamped: Multilingual speech recognition with word-level timestamps, running 100% locally in your browser thanks to ๐Ÿค— Transformers.js! This unlocks a world of possibilities for in-browser video editing! ๐Ÿคฏ What will you build? ๐Ÿ˜ Demo (+ source code) ๐Ÿ‘‡
0:37

Introducing Whisper Timestamped: Multilingual speech recognition with word-level timestamps, running 100% locally in your browser thanks to ๐Ÿค— Transformers.js! This unlocks a world of possibilities for in-browser video editing! ๐Ÿคฏ What will you build? ๐Ÿ˜ Demo (+ source code) ๐Ÿ‘‡

Xenova

105,963 Aufrufe โ€ข vor 1 Jahr

๐Ÿš€ Introducing Browser AI: Run powerful LLMs directly in your browser! ๐Ÿ”’ Complete privacy - no servers needed ๐Ÿ’ป 100% client-side processing โšก๏ธ Fast & lightweight Experience the future of web AI! Github Repo in the comments!
1:31

๐Ÿš€ Introducing Browser AI: Run powerful LLMs directly in your browser! ๐Ÿ”’ Complete privacy - no servers needed ๐Ÿ’ป 100% client-side processing โšก๏ธ Fast & lightweight Experience the future of web AI! Github Repo in the comments!

Saurav Panda

51,499 Aufrufe โ€ข vor 1 Jahr

Introducing MusicGen Web: AI-powered music generation directly in your browser, built with ๐Ÿค— Transformers.js! ๐ŸŽต Everything runs 100% locally, meaning no calls to an API! ๐Ÿคฏ Served as a static website... this costs $0 to host and run! ๐Ÿ”ฅ Try it out yourself! ๐Ÿ‘‡
0:20

Introducing MusicGen Web: AI-powered music generation directly in your browser, built with ๐Ÿค— Transformers.js! ๐ŸŽต Everything runs 100% locally, meaning no calls to an API! ๐Ÿคฏ Served as a static website... this costs $0 to host and run! ๐Ÿ”ฅ Try it out yourself! ๐Ÿ‘‡

Xenova

31,211 Aufrufe โ€ข vor 2 Jahren

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. ๐Ÿš€ The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by ๐Ÿค— Transformers.js!
0:34

IBM just released Granite 4.0, their latest series of small language models! These models excel at agentic workflows (tool calling), document analysis, RAG, and more. ๐Ÿš€ The "Micro" (3.4B) model can even run 100% locally in your browser on WebGPU, powered by ๐Ÿค— Transformers.js!

Xenova

82,893 Aufrufe โ€ข vor 9 Monaten

Apple released FastVLM so I tried vibe coding a video captioning AI app with it took 5 prompts to get a working app in anycoder and deployed it on Hugging Face 85x faster and 3.4x smaller than comparable sized VLMs the deployed app works 100% locally in your browser powered by transformers.js and WebGPU
1:56

Apple released FastVLM so I tried vibe coding a video captioning AI app with it took 5 prompts to get a working app in anycoder and deployed it on Hugging Face 85x faster and 3.4x smaller than comparable sized VLMs the deployed app works 100% locally in your browser powered by transformers.js and WebGPU

AK

42,677 Aufrufe โ€ข vor 10 Monaten

NEW: Alibaba just released Qwen 3.5 Small โ€” a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! ๐Ÿคฏ
0:46

NEW: Alibaba just released Qwen 3.5 Small โ€” a family of powerful multimodal models available in a range of sizes (0.8B, 2B, 4B, and 9B parameters). Perfect for on-device applications! They can even run 100% locally in your browser on WebGPU, powered by Transformers.js! ๐Ÿคฏ

Xenova

102,592 Aufrufe โ€ข vor 3 Monaten

"Free, accurate voice transcription in the browser using Whisper" โšก๏ธ I'm happy to share a modern voice-to-text app (Say) that uses in-browser AI (Whisper and T5) to offer voice transcription, text summaries and note management. Everything is done locally in a privacy-friendly way. Built with React and Transformers.js by Xenova
1:27

"Free, accurate voice transcription in the browser using Whisper" โšก๏ธ I'm happy to share a modern voice-to-text app (Say) that uses in-browser AI (Whisper and T5) to offer voice transcription, text summaries and note management. Everything is done locally in a privacy-friendly way. Built with React and Transformers.js by Xenova

Addy Osmani

36,822 Aufrufe โ€ข vor 1 Jahr

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. โšก๏ธ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! ๐Ÿคฏ Try it yourself! ๐Ÿ‘‡
1:28

Introducing Supertonic WebGPU: blazingly fast text-to-speech running 100% locally in your browser. โšก๏ธ Generate free audiobooks in seconds, no installation required. In this example, I created a 5-hour audiobook of The Great Gatsby in less than 3 minutes! ๐Ÿคฏ Try it yourself! ๐Ÿ‘‡

Xenova

23,474 Aufrufe โ€ข vor 7 Monaten

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! ๐Ÿค—๐Ÿคฏ It supports tasks like image captioning, optical character recognition, object detection, and many more! ๐Ÿ˜ WOW! Demo (+ source code) ๐Ÿ‘‡
1:05

Florence-2, the new vision foundation model by Microsoft, can now run 100% locally in your browser on WebGPU, thanks to Transformers.js! ๐Ÿค—๐Ÿคฏ It supports tasks like image captioning, optical character recognition, object detection, and many more! ๐Ÿ˜ WOW! Demo (+ source code) ๐Ÿ‘‡

Xenova

88,747 Aufrufe โ€ข vor 2 Jahren

WebGPU is INSANE! ๐Ÿคฏ Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. โšก๏ธ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.
1:05

WebGPU is INSANE! ๐Ÿคฏ Here's a 24B parameter model running locally in a web browser, at a blazing ~50 tokens/second on my M4 Max. โšก๏ธ It's the largest model we've ever run with Transformers.js... and we're not stopping here. Big announcement soon.

Xenova

36,159 Aufrufe โ€ข vor 3 Monaten