正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Excited to introduce Fish Speech 1.4 - now open-source and more powerful than ever! 🎉 Our mission is to make cutting-edge voice tech accessible to everyone. What's new: - Trained on 700k hours of multilingual data (up from 200k) - Now supports 8 languages: English, Chinese, German, Japanese, French,... Spanish, Korean, and Arabic - Fully open-source, empowering developers and researchers worldwide Key features: - Lightning-fast TTS with ultra-low latency - Instant voice cloning - Self-host or use our cloud service - Simple, flat-rate pricing Try it out: - Playground: - GitHub: - HuggingFace Model: - Demo: - Product Hunt: We can't wait to see what you'll create with Fish Audio. Happy voice building! 🎧🐠show more

Fish Audio

10,614 subscribers

149,977 次观看 • 1 年前 •via X (Twitter)

科学技术教育艺术

Anya Rossi• Live Now

Private livecam show

10 条评论

AT 的头像

AT1 年前

Not bad, but we need to add Russian.

Fish Audio 的头像

Fish Audio1 年前

Plan to add in next major release.

Pranay Suyash 的头像

Pranay Suyash1 年前

any indic languages in the pipeline?

Udit Goenka 的头像

Udit Goenka1 年前

Just tested...Instant voice clone requires some work, specially with Indian English accept. The sample for training data is too less. Other than that, great work on open sourcing it!

ChatBoo - AI Companion 的头像

ChatBoo - AI Companion1 年前

Can I confirm the license? GitHub and HF both say non commercial. But your post uses the term open source which has a strong meaning

ryu 的头像

ryu1 年前

Congrats!

ChatBoo - AI Companion 的头像

ChatBoo - AI Companion1 年前

Does your API offer streaming? What is the expected latency? Am I correct in understanding that your pricing is $15USD per million bytes?

Fish Audio 的头像

Fish Audio1 年前

Yes, the API does support streaming, the current E2E latency is around 400ms, we are working with our providers to further cut-down network latency.

Tonado 的头像

Tonado1 年前

正好需要一个，替代剪映会员的克隆声音功能，剪映要一个月要59来着，而且只给很有限的点数

UnShelledSec 的头像

UnShelledSec1 年前

When portuguese?

相关视频

Introducing Fish Speech 1.5 🎉 - Making state-of-the-art TTS accessible to everyone! Highlights: - #2 ranked on TTS-Arena (as "Anonymous Sparkle") - 1M hours of multilingual training data - 13 languages supported, including English, Chinese, Japanese & more - <150ms latency with high-quality instant voice cloning - Pretrained model now open source - Cost-effective self-hosting or cloud options Let's check out the details 🧵⬇️

Introducing Fish Speech 1.5 🎉 - Making state-of-the-art TTS accessible to everyone! Highlights: - #2 ranked on TTS-Arena (as "Anonymous Sparkle") - 1M hours of multilingual training data - 13 languages supported, including English, Chinese, Japanese & more - <150ms latency with high-quality instant voice cloning - Pretrained model now open source - Cost-effective self-hosting or cloud options Let's check out the details 🧵⬇️

Fish Audio

101,606 次观看 • 1 年前

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

Introducing Indic Parler-TTS: Open-Source Text-to-Speech for Over a Billion Indic Speakers! 🌏 In collaboration with Hugging Face, we are excited to release Indic Parler-TTS, a state-of-the-art open-source text-to-speech system designed to bring accessible and high-quality speech technology to India’s diverse linguistic community. Supporting 20 of the 22 scheduled Indian languages—and English in various accents (US, British, Indian)—it’s built to serve over a billion speakers and empower companies, developers, researchers, and communities. Why Indic Parler-TTS Stands Out: 1. Open and Accessible: Fully open-source with permissive licensing for unrestricted usage. 2. Wide Language Support: Includes a vast range of Indic languages, with rich diversity in voices. 3. High-Quality Audio: Produces natural, clear, and lifelike speech. 4. Adaptable and Fine-Tunable: Customize it to new languages, accents, or specific applications. 5. State-of-the-Art Performance: Proven through rigorous evaluation. 6. Versatile and Inclusive: Indic Parler-TTS offers 69 unique voices across 18 Indian languages, making it a perfect fit for diverse use cases like audiobooks, virtual assistants, and educational tools. Let's democratize speech technology together and make speech technology more inclusive and accessible for everyone. ▶️ Experience it now: Demo: Model page:

AI4Bharat

28,586 次观看 • 1 年前

With Invincible Voice, we help people living with ALS communicate more easily. Encountering Olivier Goy, an entrepreneur who lives with ALS and relentlessly fights to help all patients, made it obvious that our cutting-edge voice AI should help. We turned our Unmute voice-wrapper into a new system that 1/ transcribes interlocutor’s speech in real time, 2/ suggests various relevant responses via a personalised language model, 3/ utters patient's chosen response with their voice (using 10s pre-disease speech recordings). True to our philosophy, we open-source Invincible Voice, so that developers can refine the prototype, port it from French to other languages, adapt it to other conditions (aphasia, neurodegenerative diseases) and turn it into a deployable product. Its modularity also allows it to leverage technologies developed by Gradium that supports Invincible Voice by granting it free access to its multilingual speech models.

With Invincible Voice, we help people living with ALS communicate more easily. Encountering Olivier Goy, an entrepreneur who lives with ALS and relentlessly fights to help all patients, made it obvious that our cutting-edge voice AI should help. We turned our Unmute voice-wrapper into a new system that 1/ transcribes interlocutor’s speech in real time, 2/ suggests various relevant responses via a personalised language model, 3/ utters patient's chosen response with their voice (using 10s pre-disease speech recordings). True to our philosophy, we open-source Invincible Voice, so that developers can refine the prototype, port it from French to other languages, adapt it to other conditions (aphasia, neurodegenerative diseases) and turn it into a deployable product. Its modularity also allows it to leverage technologies developed by Gradium that supports Invincible Voice by granting it free access to its multilingual speech models.

kyutai

11,070 次观看 • 5 个月前

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

Smart Turn v2: open source, native audio turn detection in 14 languages. New checkpoint of the open source, open data, open training code, semantic VAD model on Hugging Face, fal, and Pipecat AI. - 3x faster inference (12ms on an L40) - 14 languages (13 more than v1, which was english-only) - New synthetic data set `chirp_3_all` with ~163k audio samples - 99% accuracy on held out `human_5_all` test data Good turn detection is critical for voice agents. This model "understands" both semantic and audio patterns, and mitigates the voice AI trade-off between unwanted turn latency vs the agent interrupting people before they are finished speaking. Training scripts for both Modal and local training are in the repo. We want to make it as easy as possible to contribute to or customize this model! Here's a demo running the smart-turn model with default settings, aimed at generally hitting 400ms total turn detection time. You can tune things to be faster, too. You can help by contributing data, doing architecture expermints, or cleaning open source data! Keep reading ...

kwindla

42,219 次观看 • 1 年前

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

OpenBMB

557,835 次观看 • 3 个月前

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Text-to-speech is moving way too fast. Just a few days ago, I tweeted about PersonaPlex-7B, NVIDIA's new open source TTS ( And today, Qwen just open-sourced Qwen3-TTS 🤯 It’s a revolutionary text-to-speech model built for control. Not just about generating speech, but about shaping how it sounds directly from language. You can guide the pace, the tone, and the expressiveness straight from text, without touching audio graphs or hand-tuning parameters. That’s the real shift! What makes Qwen3-TTS stand out is how practical it already is: → voice cloning from just a few seconds of audio → voice creation without any reference sample → support for 10 languages out of the box → end-to-end latency down to ~97ms → works in both streaming and non-streaming setups The models come in two sizes (0.6B and 1.7B), so you can trade off quality and hardware cost depending on your setup. You can work with curated voices, designed voices, or cloned ones, and it integrates cleanly with vLLM for production use. It also ships as a simple Python package you can pip install. If you’re building real-time voice systems, this removes a lot of friction! 100% free and open source. I put the repo in the 🧵↓

Charly Wargnier

59,144 次观看 • 5 个月前

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,484 次观看 • 1 年前

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

🚨 JUST IN: MICROSOFT just open sourced a VOICE AI THAT TRANSCRIBES 60 MINUTES OF AUDIO in a single pass. 100% FREE. It knows who spoke. It knows when they spoke. It knows exactly what they said. All in one shot. No chunking. No context loss. It's called VibeVoice. Not a transcription tool. Not a basic speech to text wrapper. A frontier voice AI family with ASR, TTS, and real time streaming. All open source. All free. Here's what it actually does 👇 VibeVoice ASR - Speech Recognition: → Processes 60 minutes of continuous audio in a single pass → Never slices audio into chunks so global context is never lost → Identifies WHO spoke, WHEN they spoke and WHAT they said simultaneously → Supports customized hotwords for domain specific accuracy → Works in 50+ languages natively → Already adopted by Hugging Face Transformers library → Already being built on by the open source community BY PEOPLE WHO HAD NO IDEA THIS LEVEL OF ACCURACY WAS ALREADY FREE. VibeVoice TTS - Text to Speech: → Generates up to 90 minutes of speech in a single pass → Supports up to 4 distinct speakers in one conversation → Natural turn taking and speaker consistency throughout → Expressive speech that captures emotional nuances → Supports English, Chinese and multiple other languages VibeVoice Realtime - Streaming TTS: → Only 300 millisecond first audible latency → Streams text input in real time → 0.5B parameters so it actually deploys anywhere → Robust long form generation up to 10 minutes → Lightweight enough for production use today The core innovation nobody is talking about: Most voice AI models slice long audio into short chunks. Every time they slice, they lose context. Speaker tracking breaks. Semantic coherence breaks. Accuracy drops. VibeVoice uses continuous speech tokenizers running at an ultra low frame rate of 7.5 Hz. This preserves audio fidelity while dramatically boosting computational efficiency. The entire 60 minutes stays in context. Nothing gets lost. Nobody gets misidentified. The numbers: → VibeVoice ASR 7B - available now on Hugging Face → VibeVoice Realtime 0.5B - try it on Colab right now → 50+ supported languages → 11 distinct English voice styles → 9 multilingual speaker voices → Already integrated into Hugging Face Transformers → Finetuning code now available The wildest part? A voice powered input method called Vibing just built itself on top of VibeVoice ASR. Available on macOS and Windows right now. The open source community is already shipping products on top of this. 100% Open Source. Free to use. Free to fine tune. Free to build on. 🔖 Save this before your competitors find it first. 👇

Kanika

220,656 次观看 • 3 个月前

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Microsoft did it again! Speech AI models have a major limitation. They slice long recordings into tiny chunks, lose track of who's speaking, and forget all context halfway through. This is exactly what Microsoft's VibeVoice solves. It's an open-source family of frontier voice AI models for both speech recognition and speech generation. Here's what it can do: > VibeVoice-ASR processes up to 60 minutes of audio in a single pass. No chunking. It outputs structured transcriptions with who spoke, when they spoke, and what they said. > You can feed it custom hotwords like names, technical jargon, or domain-specific terms. The model uses them to significantly improve accuracy on specialized content. > VibeVoice-TTS generates up to 90 minutes of multi-speaker speech with up to 4 distinct speakers. Natural turn-taking, emotional expression, all in one pass. > VibeVoice-Realtime is a 0.5B streaming TTS model with ~300ms first-audio latency. Small enough to deploy practically anywhere. All of this is powered by continuous speech tokenizers running at just 7.5 Hz. This ultra-low frame rate preserves audio quality while making long sequences computationally feasible. I have shared the link to the GitHub repo in the replies!

Akshay 🚀

45,206 次观看 • 3 个月前

It’s hard to believe that 3 years ago, none of this was possible. Now, it’s pretty much going to change everything. Last month, Fish Audio reached out to me to try their voice AI software. They just launched their new S1 model today, and I was curious about the state of AI and voice (and everything else), so I gave it a spin. I liked it enough that when I was asked about a partnership, I said yes. I’m free to talk about what I like and don’t like about the software, and I’m going to share with you a few voices I cloned as well as some of the workflow. It was much easier than I thought. To give you an example, here is a private (research only) voice I cloned as a test. I grabbed a clip of Rutger Hauer’s famous speech from Blade Runner and uploaded it to the voice cloner on the Fish Audio Website as a private voice (no one else can use it, as it is for research only). I didn’t think it would work. The audio sample is very short. But Fish Audio was able to clone the voice extremely well and very fast. I didn’t have to upload any more than that to produce these results. I used Grok to write the new dialog, and I added the rain and background effects and the result is pretty impressive. It only took just a few minutes once I had the audio uploaded for everything from cloning to generating multiple takes. I’ll give some tips and pointers on how to get the best results at the conclusion of this thread and show you some surprising things it can do. (con’t) #Promotion

It’s hard to believe that 3 years ago, none of this was possible. Now, it’s pretty much going to change everything. Last month, Fish Audio reached out to me to try their voice AI software. They just launched their new S1 model today, and I was curious about the state of AI and voice (and everything else), so I gave it a spin. I liked it enough that when I was asked about a partnership, I said yes. I’m free to talk about what I like and don’t like about the software, and I’m going to share with you a few voices I cloned as well as some of the workflow. It was much easier than I thought. To give you an example, here is a private (research only) voice I cloned as a test. I grabbed a clip of Rutger Hauer’s famous speech from Blade Runner and uploaded it to the voice cloner on the Fish Audio Website as a private voice (no one else can use it, as it is for research only). I didn’t think it would work. The audio sample is very short. But Fish Audio was able to clone the voice extremely well and very fast. I didn’t have to upload any more than that to produce these results. I used Grok to write the new dialog, and I added the rain and background effects and the result is pretty impressive. It only took just a few minutes once I had the audio uploaded for everything from cloning to generating multiple takes. I’ll give some tips and pointers on how to get the best results at the conclusion of this thread and show you some surprising things it can do. (con’t) #Promotion

Grummz

69,859 次观看 • 1 年前

Good morning from Washington. Time for a quick tour. You know what you won’t find in my office? A desk. Or a chief of staff. We have an open office with all day interaction and collaboration between my employees. As for the chief of staff? I tried having a single point of failure before. Didn’t love it. Now our four directors report directly to me. Our office works faster, more efficient and better than it ever has under this set up. Everyone in the office has a voice and they are encouraged to use it. Our entire office is on the same page with the way we serve our constituents. And we love it. Now

Good morning from Washington. Time for a quick tour. You know what you won’t find in my office? A desk. Or a chief of staff. We have an open office with all day interaction and collaboration between my employees. As for the chief of staff? I tried having a single point of failure before. Didn’t love it. Now our four directors report directly to me. Our office works faster, more efficient and better than it ever has under this set up. Everyone in the office has a voice and they are encouraged to use it. Our entire office is on the same page with the way we serve our constituents. And we love it. Now

Rep. Nancy Mace

544,697 次观看 • 5 个月前

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

NOBODY wants to send their data to Google or OpenAI. Yet here we are, shipping proprietary code, customer information, and sensitive business logic to closed-source APIs we don't control. While everyone's chasing the latest closed-source releases, open-source models are quietly becoming the practical choice for many production systems. Here's what everyone is missing: Open-source models are catching up fast, and they bring something the big labs can't: privacy, speed, and control. I built a playground to test this myself. Used CometML's Opik to evaluate models on real code generation tasks - testing correctness, readability, and best practices against actual GitHub repos. Here's what surprised me: OSS models like MiniMax-M2, Kimi k2 performed on par with the likes of Gemini 3 and Claude Sonnet 4.5 on most tasks. But practically MiniMax-M2 turns out to be a winner as it's twice as fast and 12x cheaper when you compare it to models like Sonnet 4.5. Well, this isn't just about saving money. When your model is smaller and faster, you can deploy it in places closed-source APIs can't reach: ↳ Real-time applications that need sub-second responses ↳ Edge devices where latency kills user experience ↳ On-premise systems where data never leaves your infrastructure MiniMax-M2 runs with only 10B activated parameters. That efficiency means lower latency, higher throughput, and the ability to handle interactive agents without breaking the bank. The intelligence-to-cost ratio here changes what's possible. You're not choosing between quality and affordability anymore. You're not sacrificing privacy for performance. The gap is closing, and in many cases, it's already closed. If you're building anything that needs to be fast, private, or deployed at scale, it's worth taking a look at what's now available. MiniMax-M2 is 100% open-source, free for developers right now. I have shared the link to their GitHub repo in the next tweet. You will also find the code for the playground and evaluations I've done.

Akshay 🚀

50,323 次观看 • 7 个月前

Locked and loaded 💥 Openwork is now Accomplish v0.3.4 released today (download from link in bio): - Following the announcement from Kimi.ai a couple of hours ago, we are happy to introduce support for Kimi K2.5 with a new Moonshot AI integration! This is a global SOTA model for CUA BrowseComp (74.9%) - Log in with your OpenAI account (using OAuth) instead of providing an API key! This is both more seurce and it allows you to leverage existing OpenAI plan/subscription. - Support for Microsoft Azure AI Foundry thanks to our friends from Microsoft (cheers Ido Frizler!) - Support for LM Studio to run models locally (cheers to Yossi Elkrief LM Studiodevs!) . Try qwen/qwen3-vl-8b! - Support for MiniMax (official), the awesome open source models we love (thanks marcho) - You can now voice chat with openwork, courtesy of ! Thank you Max (Zihan) ZENG! Watch Openwork is now Accomplish one-shotting SOC 2 Compliance gap analysis (scanning your GitHub, Jira, Notion, websites and more):

Locked and loaded 💥 Openwork is now Accomplish v0.3.4 released today (download from link in bio): - Following the announcement from Kimi.ai a couple of hours ago, we are happy to introduce support for Kimi K2.5 with a new Moonshot AI integration! This is a global SOTA model for CUA BrowseComp (74.9%) - Log in with your OpenAI account (using OAuth) instead of providing an API key! This is both more seurce and it allows you to leverage existing OpenAI plan/subscription. - Support for Microsoft Azure AI Foundry thanks to our friends from Microsoft (cheers Ido Frizler!) - Support for LM Studio to run models locally (cheers to Yossi Elkrief LM Studiodevs!) . Try qwen/qwen3-vl-8b! - Support for MiniMax (official), the awesome open source models we love (thanks marcho) - You can now voice chat with openwork, courtesy of ! Thank you Max (Zihan) ZENG! Watch Openwork is now Accomplish one-shotting SOC 2 Compliance gap analysis (scanning your GitHub, Jira, Notion, websites and more):

Or Hiltch

33,832 次观看 • 5 个月前

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

Cerebras inference is very fast. So fast that it changes how we think about configuring our LLMs for voice agent use cases. Kimi K2.6 is a 1T parameter reasoning model that Cerebras serves at 650 - 1,000 tokens per second (end-to-end throughput), with time to first token metrics as low as 150ms (latency). These numbers are two to three times faster than other similarly capable models. The biggest lever we get from this kind of speed is that we can use the model in reasoning mode, and still have excellent "time to first non-thinking token." This solves a big pain point we have in 2026 for voice agent use cases. Almost all recent innovation in post-training has focused on making models good at reasoning ("test time compute"). This is great, but it makes the user-facing model latency much, much slower. Which is a problem for conversational voice agents. We can run Kimi K2.6 with reasoning turned on, and get responses faster than other models produce with reasoning disabled. On my 30-turn voice agent benchmark, Kimi K2.6 with reasoning enabled ties GPT 5.1 and Haiku 4.5 with reasoning disabled, and is still about 200ms seconds faster! On my primary task agent benchmark, Kimi K2.6 is now the #2 model. It ranks just behind Gemini 3.5 Flash in "high" reasoning mode, and tied with GLM 5, Sonnet 4.6, and GPT 5.4 with reasoning set to "low." But Kimi K2.6 completes each turn in the agent loop in under 500ms. The other four models are all at least 3x slower. (Models only qualify for this benchmark if they can complete task turns at a P50 <4s.) A couple of other things that this speed buys us, for production voice agents: - Tool calls happen fast enough that we don't have to work around tool call latency in our pipeline design. - We can prompt the model to output structured data at the beginning of a response, followed by plain text for voice generation. This opens up possibilities like asking the model to do complex classification/generation tasks that influence the rest of the pipeline. For example, the model could create a detailed style prompt for a steerable TTS model, for each individual conversation turn. And, of course, you can use Kimi K2.6 with reasoning turned off. Cerebras calls this "instant" mode. Here's a video of a Cerebras Kimi K2.6 voice agent with voice-to-voice response time, measured at the client, under 500ms. This is the true response latency as perceived by the user, including all network and audio codec overhead, transcription and turn detection, Kimi K2.6 token generation, and voice generation. 500ms is, effectively, instant. So the Cerebras naming for this mode is a propos. :-)

kwindla

40,319 次观看 • 1 个月前

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

Open science is how we continue to push technology forward and today at Meta FAIR we’re sharing eight new AI research artifacts including new models, datasets and code to inspire innovation in the community. More in the video from Joelle Pineau. This work is another important step towards our goal of achieving Advanced Machine Intelligence (AMI). What we’re releasing: • Meta Spirit LM: An open source language model for seamless speech and text integration. • Meta Segment Anything Model 2.1: An updated checkpoint with improved results on visually similar objects, small objects and occlusion handling. Plus a new developer suite to make it easier for developers to build with SAM 2. • Layer Skip: Inference code and fine-tuned checkpoints demonstrating a new method for enhancing LLM performance. • SALSA: New code to enable researchers to benchmark AI-based attacks in support of validating security for post-quantum cryptography. • Meta Lingua: A lightweight and self-contained codebase designed to train language models at scale. • Meta Open Materials: New open source models and the largest dataset of its kind to accelerate AI-driven discovery of new inorganic materials. • MEXMA: A new research paper and code for our novel pre-trained cross-lingual sentence encoder with coverage across 80 languages. • Self-Taught Evaluator: a new method for generating synthetic preference data to train reward models without relying on human annotations. Access to state-of-the-art AI creates opportunities for everyone. We’re excited to share this work and look forward to seeing the community innovation that results from it. Details and access to everything released by FAIR today ➡️

AI at Meta

150,222 次观看 • 1 年前

🦙 Since you loved NotebookLlaMa, our open-source, LlamaCloud-backed NotebookLM alternative, we decided to give you more features! In the latest release you can: 📊 Extract and download images and tables from your files, and interactively visualize all tabular data ✅ Chat with your document and verify immediately everything that AI is saying about it, using the new claim verification and citation finding functionality 👇 Watch the video below for a full demo of the new functionalities 👩‍💻🧑‍💻 There is also a bonus: thanks to the community effort and contribution, you can now customize the embedding model you want to use to build the LlamaCloud index, through a textualize.io CLI! ⭐ Star NotebookLlaMa on GitHub: 🦙☁️ Sign-up for LlamaCloud and test our awesome products: 📚 Learn more about LlamaCloud:

🦙 Since you loved NotebookLlaMa, our open-source, LlamaCloud-backed NotebookLM alternative, we decided to give you more features! In the latest release you can: 📊 Extract and download images and tables from your files, and interactively visualize all tabular data ✅ Chat with your document and verify immediately everything that AI is saying about it, using the new claim verification and citation finding functionality 👇 Watch the video below for a full demo of the new functionalities 👩‍💻🧑‍💻 There is also a bonus: thanks to the community effort and contribution, you can now customize the embedding model you want to use to build the LlamaCloud index, through a textualize.io CLI! ⭐ Star NotebookLlaMa on GitHub: 🦙☁️ Sign-up for LlamaCloud and test our awesome products: 📚 Learn more about LlamaCloud:

LlamaIndex 🦙

11,466 次观看 • 1 年前

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

We've officially released and open-sourced HunyuanImage 2.1, our latest text-to-image model. The new model delivers on our commitment to balancing performance and quality. With native 2K image generation, HunyuanImage 2.1 is an advanced open-source text-to-image model.🎨 ✨ New in 2.1: 🔹Advanced Semantics: Supports ultra-long and complex prompts of up to 1000 tokens, and precisely controls the generation of multiple subjects in a single image. 🔹Precise Chinese and English Text Rendering with seamless image–text integration: The model naturally integrates text into images, making it suitable for a wide range of applications such as product covers, illustrations, and poster design to meet the needs of various fields. 🔹Rich Styles and High Aesthetic: Capable of generating images in various styles—including photorealistic portraits, comics, and vinyl figures—it delivers outstanding visual appeal and artistic quality. 🔹High-Quality Generation: Efficiently produces ultra-high-definition (2K) images in the same time other models take to generate a 1K image. HunyuanImage 2.1 uses two text encoders: a multimodal large language model (MLLM) to improve the model's image and text alignment capabilities, and a multi-language character-aware encoder to improve text rendering capabilities. The model is a single- and double-stream diffusion transformer with 17B parameters. We've also open-sourced the weights of the the accelerated version with meanflow which reduces inference steps from 100 to just 8, and PromptEnhancer, the first industrial-grade rewriting model that enhances your prompts for more nuanced and expressive image generation. Now, creators turn complex ideas—like posters with slogans or multi-panel comics—into visuals faster than ever. We’re just getting started. Stay tuned for our native multimodal image generation model coming soon. 🌐Website: 🔗Github: 🤗Hugging Face: ✨Hugging Face Demo:

Tencent Hy

89,257 次观看 • 10 个月前