Загрузка видео...

Не удалось загрузить видео

На главную

Listen, speak, handle interruptions, and call tools in one live conversation. 🎙️ Introducing NVIDIA-NemotronLabs-VoiceChat-11B, NVIDIA’s end-to-end full-duplex model for real-time voice agents. 🤖 🏆 It ranks #2 among open full-duplex models on both VoiceBench and Full-Duplex-Bench 1.0. ⚡ Natural turn-taking responds in ~448 ms, while barge-in lets users interrupt...

ModelScope2022's profile picture

ModelScope

12,474 subscribers

22,194 просмотров • 26 дней назад •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.
2:32

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.

Coin Bureau

29,085 просмотров • 1 месяц назад

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.
0:42

NVIDIA just removed the biggest friction point in Voice AI 🤯 They've open-sourced PersonaPlex-7B, a full-duplex conversational model that can listen and speak at the same time. Instead of waiting for you to finish talking, it uses a dual-stream architecture to process and respond in real-time. 100% Open-Source and Free.

Simplifying AI

278,970 просмотров • 7 месяцев назад

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM
2:40

🥳 Introducing MiniCPM-o 4.5 The first full-duplex omni-modal LLM in open-source community 🎬🎙️ 🔥 Key Highlights: • Full-duplex Omni-modal Live Streaming: The model can see, listen, and speak simultaneously in a real-time conversation without mutual blocking • Proactive Interaction: Moving beyond reactive QA to performing proactive interaction, such as initiating reminders • Leading Performance: Scoring 77.6 on OpenCompass, it outperforms GPT-4o & Gemini 2.0 Pro in vision-language tasks with 9B params The best part? You can experience all above on your PC! #MiniCPM #OpenSource #MultimodalAI #LLM

OpenBMB

398,009 просмотров • 6 месяцев назад

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥
0:42

NVIDIA just removed one of the biggest friction points in Voice AI. PersonaPlex-7B is an open-source, full-duplex conversational model. Free, open source (MIT), with open model weights on Hugging Face 🤗 Links to repo and weights in 🧵↓ The traditional ASR → LLM → TTS pipeline forces rigid turn-taking. It’s efficient, but it never feels natural. PersonaPlex-7B changes that. This NVIDIA model can listen and speak at the same time. It runs directly on continuous audio tokens with a dual-stream transformer, generating text and audio in parallel instead of passing control between components. That unlocks: → instant back-channel responses → interruptions that feel human → real conversational rhythm Persona control is fully zero-shot! If you’re building low-latency assistants or support agents, this is a big step forward 🔥

Chaz Wargnier ♨️

565,811 просмотров • 7 месяцев назад

How far are we from "Her"? I couldn't help but wonder, given the rapid fire of GPT-Live and Thinking Machines. Turns out, full duplex speech-to-speech is not particularly new. Moshi has been around for more than 2 years. Many thanks to Neil Zeghidour for bringing so much nuance. Check out kyutai who are doing god's work and open-sourcing it (not sponsored!). 00:00 Intro 01:24 ChatGPT Standard & LLM-based cascades 04:08 ChatGPT Advanced & end-to-end speech models 05:35 ChatGPT Live & Her 07:38 Thinking Machines & multi-stream modeling 09:13 Moshi & full duplex assistants 13:24 Moshi’s inner monologue 15:38 Why aren’t full duplex models everywhere? 17:08 Tool calling in full duplex models 18:00 Moshi RAG 19:06 Is the future full duplex? 20:24 How far are we from Her?
21:29

How far are we from "Her"? I couldn't help but wonder, given the rapid fire of GPT-Live and Thinking Machines. Turns out, full duplex speech-to-speech is not particularly new. Moshi has been around for more than 2 years. Many thanks to Neil Zeghidour for bringing so much nuance. Check out kyutai who are doing god's work and open-sourcing it (not sponsored!). 00:00 Intro 01:24 ChatGPT Standard & LLM-based cascades 04:08 ChatGPT Advanced & end-to-end speech models 05:35 ChatGPT Live & Her 07:38 Thinking Machines & multi-stream modeling 09:13 Moshi & full duplex assistants 13:24 Moshi’s inner monologue 15:38 Why aren’t full duplex models everywhere? 17:08 Tool calling in full duplex models 18:00 Moshi RAG 19:06 Is the future full duplex? 20:24 How far are we from Her?

Julia Turc

73,053 просмотров • 1 месяц назад

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...
3:28

Introducing PhoneLLM, an open model for voice agents. GPT 5.6 Terra performance on typical voice agent tasks at 1/3 the latency and 1/18 the cost. For voice agents, we need models that are both very low latency and very good at tool calling and instruction following. There's a trade-off here, and we often have to compromise on either latency or capability when building voice agents. With PhoneLLM (and the training and data stack that made this model possible) we're fixing this problem. For the last couple of years, most of the effort in frontier model development has gone towards leveraging test-time compute. Which is awesome! Models of all shapes and sizes are available that perform really, really well ... if you have "thinking" turned on for your model. But if you need your agent to respond at voice conversation speed, you can't use thinking models. PhoneLLM is a full-weights fine-tune of NVIDIA Nemotron Nano 30B. We trained on a wide range of real-world telephone and customer support use cases. The training focused on taking the excellent Nano 30B base capabilities and teaching the model to do typical voice agent tasks with thinking disabled. The results are really good: accurate tool calling and concise, on-topic responses in long conversations. And fast: TTFAT measured server-side is <100ms if you run PhoneLLM on a lightly loaded B200. :-) But seriously, when we characterize model latency, we do it with full, end-to-end, batched request simulations using real Pipecat voice agent pipelines. You can serve more than 80 concurrent agents on a single B200 with P95 end-to-end TTFAT <600ms. Including network overhead. That's an LLM cost-per-minute around $0.0025. (1/4 of a cent.) At a latency lower than any third-party API offers today. More details about this model, including weights on Hugging Face, how to spin it up with one click on Modal, and a starter project repo you can clone, are in the thread ...

kwindla

313,250 просмотров • 2 дней назад

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)
3:13

OpenAI shipped a new speech-to-speech model today: gpt-realtime-2 This is the first speech-to-speech model good enough to use in my voice agents that do "real work." Or real play, for that matter. Here's gpt-realtime-2 as the brain of the ship AI in Gradient Bang. The voice-to-voice response and tool calling times here are unedited, so you can see exactly what the interaction with the model is like in an agent with a very complex system instruction and frequent tool calls. (I did clip out the subagent task execution segments, after gpt-realtime-2 starts a subagent via a tool call. Subagents in this config used gpt-5.2 "medium" effort.)

kwindla

55,222 просмотров • 3 месяцев назад

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision
1:31

MiniCPM-o 4.5: Seeing, Listening, and Speaking — All at Once. 👁️👂🗣️ ✨Beyond traditional turn-taking, we’ve built a Native Full-Duplex engine that allows a 9B model to see, listen, and speak in one concurrent, non-blocking stream. Watch how it masters real-world complexity in real-time: 🔔 Proactive Auditory Interaction: Interrupts itself to alert you when it hears a "Ding!" while reading cards. 🎨 Temporal Flow Tracking: Follows your pen in real-time, narrating and "mind-reading" your drawing as you sketch. 🍎 Omni-Perception: Scans groceries & identifies prices on the fly. ✨Why it’s a category-leader: 📌Performance: Surpasses GPT-4o and Gemini 2.0 Pro on OpenCompass (Avg. 77.6). 📌Architecture: End-to-end fusion of SigLip2, Whisper, and CosyVoice2 on a Qwen3-8B base. 📌Efficiency: Full-duplex live streaming now runs locally on PCs via llama.cpp-omni. The era of "Wait-and-Response" AI is over. Proactive, real-time intelligence is now open-source. 🚀Experience it on Hugging Face: 🔗 #MiniCPM #Omnimodal #FullDuplex #EdgeAI #OpenSource #ComputerVision

OpenBMB

115,505 просмотров • 6 месяцев назад

Today we’re releasing Chroma 1.0 → the world first open-source, end-to-end, real-time speech-to-speech model → with personalized voice cloning Trained by FlashLabs. Deployed on FlashAI👉 An open research-grade alternative to the OpenAI Realtime model. Voice Test dubbing Elon Musk and Lex Fridman: 🔥What’s real (evals and benchmarks attached): ⚡ 2× faster than real-time ) 📘 SGLang Cookbook: 📄 Paper + benchmarks: 🤗 Models: 💻 Inference code: 🔁 RT if you believe real-time AI should be open 💬 Reply if you’re building on Conversational Voice AI products
1:57

Today we’re releasing Chroma 1.0 → the world first open-source, end-to-end, real-time speech-to-speech model → with personalized voice cloning Trained by FlashLabs. Deployed on FlashAI👉 An open research-grade alternative to the OpenAI Realtime model. Voice Test dubbing Elon Musk and Lex Fridman: 🔥What’s real (evals and benchmarks attached): ⚡ 2× faster than real-time ) 📘 SGLang Cookbook: 📄 Paper + benchmarks: 🤗 Models: 💻 Inference code: 🔁 RT if you believe real-time AI should be open 💬 Reply if you’re building on Conversational Voice AI products

FlashLabs

1,249,043 просмотров • 7 месяцев назад

What if your voice AI could interrupt you the moment it figured out your question - sometimes even before you finished asking it? Last week, I sat down with Neil, CEO of Gradium and co-founder of Kyutai , to talk about the future of speech-to-speech models and why he believes today's cascaded voice systems will soon look "archaic and brittle." Some highlights from our conversation: 🎯 How Kyutai built Moshi—a full duplex conversational AI with "negative latency"—in 6 months with just 4-6 people (while big tech teams had 10-20x the resources) 🧠 Why speech-to-speech models lose intelligence compared to their text counterparts (and what's being done about it) 📱 Pocket TTS: The first voice cloning model that runs on your phone's CPU—not GPU, CPU 🤖 Why robotics and spatial audio represent the next frontier (hint: current voice systems completely break in these environments) 👶 The efficiency gap: Babies learn to speak fluently from <5,000 hours of audio. Current models train on millions of hours. We're doing something wrong. My favorite vision from Neil? The first truly contrarian AI that interrupts you mid-sentence to tell you why you're wrong. Not just more natural conversation—but actually useful for testing ideas and playing devil's advocate. Full episode and detailed blog post linked in the comments 👇 What's your take - will speech-to-speech replace cascaded systems, or will modularity keep cascaded architectures dominant even as naturalness improves?
0:57

What if your voice AI could interrupt you the moment it figured out your question - sometimes even before you finished asking it? Last week, I sat down with Neil, CEO of Gradium and co-founder of Kyutai , to talk about the future of speech-to-speech models and why he believes today's cascaded voice systems will soon look "archaic and brittle." Some highlights from our conversation: 🎯 How Kyutai built Moshi—a full duplex conversational AI with "negative latency"—in 6 months with just 4-6 people (while big tech teams had 10-20x the resources) 🧠 Why speech-to-speech models lose intelligence compared to their text counterparts (and what's being done about it) 📱 Pocket TTS: The first voice cloning model that runs on your phone's CPU—not GPU, CPU 🤖 Why robotics and spatial audio represent the next frontier (hint: current voice systems completely break in these environments) 👶 The efficiency gap: Babies learn to speak fluently from <5,000 hours of audio. Current models train on millions of hours. We're doing something wrong. My favorite vision from Neil? The first truly contrarian AI that interrupts you mid-sentence to tell you why you're wrong. Not just more natural conversation—but actually useful for testing ideas and playing devil's advocate. Full episode and detailed blog post linked in the comments 👇 What's your take - will speech-to-speech replace cascaded systems, or will modularity keep cascaded architectures dominant even as naturalness improves?

Brooke Hopkins

13,000 просмотров • 6 месяцев назад

How did a tiny, scrappy team build one of the most powerful AI voice models? In a deep dive with Sesame CTO Ankit Kumar and a16z's Anjney Midha, we explore how Sesame is pushing the boundaries of AI conversation, why it open-sourced its speech generation model, and the power of small teams to outdo much larger AI labs on product focus. A part of their secret: a relentless focus on real-time, natural conversations over raw intelligence, and a deep commitment to voice, personality, and user experience. By opening up its speech generation model, Sesame is paving the way for even more breakthroughs in AI-native conversation 👇
1:04

How did a tiny, scrappy team build one of the most powerful AI voice models? In a deep dive with Sesame CTO Ankit Kumar and a16z's Anjney Midha, we explore how Sesame is pushing the boundaries of AI conversation, why it open-sourced its speech generation model, and the power of small teams to outdo much larger AI labs on product focus. A part of their secret: a relentless focus on real-time, natural conversations over raw intelligence, and a deep commitment to voice, personality, and user experience. By opening up its speech generation model, Sesame is paving the way for even more breakthroughs in AI-native conversation 👇

a16z

29,930 просмотров • 1 год назад

You can now generate real-time speech that sounds conversational. Microsoft just open-sourced VibeVoice, a real-time text-to-speech system with ~300 ms first audio latency and streaming input. It handles long conversations without falling apart. 𝗧𝗵𝗶𝘀 𝗺𝗼𝗱𝗲𝗹 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗹𝗼𝗻𝗴, 𝗺𝘂𝗹𝘁𝗶-𝘀𝗽𝗲𝗮𝗸𝗲𝗿 𝘀𝗽𝗲𝗲𝗰𝗵. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. 𝗜𝘁 𝘄𝗼𝗿𝗸𝘀 𝗯𝘆 𝗿𝗲𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗶𝗺𝗲 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. Audio compresses into semantic and acoustic tokens. They run at 7.5 Hz instead of frame-level audio. A language model predicts structure. A diffusion head restores acoustic detail. 𝗜𝘁 𝗮𝗹𝗹𝗼𝘄𝘀 𝗹𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝘀𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗮𝘂𝗱𝗶𝗼. The real-time variant streams text incrementally. First speech arrives in ~300 ms. A WebSocket demo shows live generation. The code is MIT-licensed and research-only. The repo already passed 20k GitHub stars.
1:00

You can now generate real-time speech that sounds conversational. Microsoft just open-sourced VibeVoice, a real-time text-to-speech system with ~300 ms first audio latency and streaming input. It handles long conversations without falling apart. 𝗧𝗵𝗶𝘀 𝗺𝗼𝗱𝗲𝗹 𝗴𝗲𝗻𝗲𝗿𝗮𝘁𝗲𝘀 𝗹𝗼𝗻𝗴, 𝗺𝘂𝗹𝘁𝗶-𝘀𝗽𝗲𝗮𝗸𝗲𝗿 𝘀𝗽𝗲𝗲𝗰𝗵. It produces up to 90 minutes of audio. It supports up to four distinct speakers. Turn-taking stays consistent over long sessions. 𝗜𝘁 𝘄𝗼𝗿𝗸𝘀 𝗯𝘆 𝗿𝗲𝗱𝘂𝗰𝗶𝗻𝗴 𝘁𝗶𝗺𝗲 𝗿𝗲𝘀𝗼𝗹𝘂𝘁𝗶𝗼𝗻. Audio compresses into semantic and acoustic tokens. They run at 7.5 Hz instead of frame-level audio. A language model predicts structure. A diffusion head restores acoustic detail. 𝗜𝘁 𝗮𝗹𝗹𝗼𝘄𝘀 𝗹𝗼𝘄-𝗹𝗮𝘁𝗲𝗻𝗰𝘆 𝘀𝘁𝗿𝗲𝗮𝗺𝗶𝗻𝗴 𝗮𝘂𝗱𝗶𝗼. The real-time variant streams text incrementally. First speech arrives in ~300 ms. A WebSocket demo shows live generation. The code is MIT-licensed and research-only. The repo already passed 20k GitHub stars.

Lior Alexander

61,122 просмотров • 7 месяцев назад

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone
0:25

New LFM2.5-2.6B hits DeepSeek-V4 level on tool calling and runs 3.7x faster! We ran Liquid AI 's new LFM2.5-2.6B against DeepSeek-V4-Flash on one box with 4x RTX 5090. Both got the same three jobs, and each one only completes if the model fires every tool call Topics: -weather and local time in six cities -one budget into six currencies -four hotels checked and booked for one date Outputs: LFM2.5-2.6B: 35/35 tool-calls, 366 tok/s, 19s DeepSeek-V4-Flash: 35/35 tool-calls, 77 tok/s, 70s Both models made all 35 calls, and both fired twelve of them in one turn. LFM was trained for agents, and tool calling is where that shows. Strong result for a model you can run right on your phone

atomic.chat

112,626 просмотров • 23 дней назад

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. :-)
0:40

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

40,593 просмотров • 3 месяцев назад

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace
1:37

🚀 Introducing AgentCPM-Explore: The First Open-Source 4B-Agent Model to Conquer GAIA & Complex Real-World Tasks! 🤗 Hugging Face: 🔗 GitHub: ✨ Key Highlights: ✅ SOTA Agentic Performance: Sets a new benchmark for 4B-scale agent models—outperforming all peers, surpassing 8B models, and rivaling select 30B+ and closed-source LLMs. 🧠 Deep Research Capability: Excels at long-horizon reasoning, supports 100+ turns of autonomous interaction with multi-source cross-validation, human-like self-correction, and dynamic tool use + strategy adaptation—just like a real researcher! 🔓 Full-Stack Open Source: We’re open-sourcing the entire end-to-end agent stack—not just the model! Empower your own innovations with - AgentRL: Asynchronous reinforcement learning framework - AgentDock: Secure, extensible tool sandbox - AgentToLeaP: An one-click evaluation platform for agent tool-learning capabilitie - Full training data pipeline & reproducible workflows #AgentCPM #OpenSourceAI #AgenticAI #AI #GAIA #LLM #OpenBMB #AIAgents #HuggingFace

OpenBMB

13,996 просмотров • 7 месяцев назад

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.
1:39

QVAC SDK 0.13.0 is live, and this version brings a lot of exciting updates! Local AI now plugs into your coding agent, ships as a desktop app in one command, and runs even more models. Highlights: NEW INTEGRATIONS - OpenCode and coding agents: the new @qvac/ai-sdk-provider makes QVAC a local provider. Less setup, same-model requests queue cleanly, and managed mode starts and supervises qvac serve for you. - Broader OpenAI-compatible API, validated across supported flows so covered capabilities stay consistent and testable. - Turn your QVAC project into a real desktop app for Mac, Windows, or Linux with a single command. The new Electron plugin handles the packaging and keeps the app small by including only what it needs. NEW MODELS - New pi0.5 model support - run a vision-language "robot brain" on a single ordinary graphics card, at full accuracy. - Image-to-video, fully local, via the Wan2.1 model in the Diffusion addon. - New BCI add-on: brain-computer interface transcription, fully local. Decode recorded neural signals into text on-device via the Whisper.cpp-based BCI model. IMPROVEMENTS - Whisper GPU transcription on Android, auto-picking the best backend (OpenCL on Adreno 700+, Vulkan elsewhere), unified on one ggml engine. - Parakeet steadier on mobile, with real end-of-utterance detection for streaming. - Supertonic TTS now runs full GPU across Metal, Vulkan, and OpenCL, with native streaming.

QVAC

20,931,912 просмотров • 2 месяцев назад

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 🧵↓
0:41

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 просмотров • 7 месяцев назад

NVIDIA AI Releases Nemotron 3 Embed: An Open Embedding Collection Whose 8B Checkpoint Ranks #1 on RTEB Most RAG stacks treat the embedding model as a commodity — pick one, index, move on. Nemotron 3 Embed is NVIDIA's argument that the retrieval layer is where agent cost actually gets set. They released three open checkpoints — Nemotron-3-Embed-8B-BF16, 1B-BF16, and 1B-NVFP4 — built on Ministral bases, trained with bidirectional attention masking, pooled by averaging token-level representations, all taking 32,768-token inputs under OpenMDW-1.1. Here's what's actually interesting: → The 8B ranks #1 overall on RTEB: 78.46 avg NDCG@10, alongside 75.45 on MMTEB Retrieval and 60.60 on ViDoRe-V3 text → The 1B wasn't trained small. It was pruned from a 3B parent with ModelOpt mcore_minitron NAS, then distilled from the 8B teacher on COS + MSE loss — twice → That pipeline lands the 1.14B checkpoint at 72.38 RTEB, up 10.4 points on the prior-generation llama-nemotron-embed-vl-1b-v2 → NVFP4 costs 0.38 RTEB points (72.00 vs 72.38, ~99.5% retention) and buys up to 2x BF16 throughput on Blackwell Full Analysis: Model weight: Technical details: NVIDIA AI NVIDIA
0:35

NVIDIA AI Releases Nemotron 3 Embed: An Open Embedding Collection Whose 8B Checkpoint Ranks #1 on RTEB Most RAG stacks treat the embedding model as a commodity — pick one, index, move on. Nemotron 3 Embed is NVIDIA's argument that the retrieval layer is where agent cost actually gets set. They released three open checkpoints — Nemotron-3-Embed-8B-BF16, 1B-BF16, and 1B-NVFP4 — built on Ministral bases, trained with bidirectional attention masking, pooled by averaging token-level representations, all taking 32,768-token inputs under OpenMDW-1.1. Here's what's actually interesting: → The 8B ranks #1 overall on RTEB: 78.46 avg NDCG@10, alongside 75.45 on MMTEB Retrieval and 60.60 on ViDoRe-V3 text → The 1B wasn't trained small. It was pruned from a 3B parent with ModelOpt mcore_minitron NAS, then distilled from the 8B teacher on COS + MSE loss — twice → That pipeline lands the 1.14B checkpoint at 72.38 RTEB, up 10.4 points on the prior-generation llama-nemotron-embed-vl-1b-v2 → NVFP4 costs 0.38 RTEB points (72.00 vs 72.38, ~99.5% retention) and buys up to 2x BF16 throughput on Blackwell Full Analysis: Model weight: Technical details: NVIDIA AI NVIDIA

Marktechpost AI

32,352 просмотров • 1 месяц назад

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now
0:43

MICROSOFT DROPPED A 4B PARAMETER MODEL THAT TURNS ONE IMAGE INTO A 3D ASSET IN 3 SECONDS and it's open source TRELLIS.2 fully textured, physically accurate 3D models with PBR textures out of the box not a rough mesh..not a placeholder roughness, metallic, opacity the kind of detail that makes things look real under any lighting and it handles the weird stuff too..open surfaces, hollow interiors, geometry that breaks every other tool the model doesn't know the word "limitation" apparently demo is live on hugging face right now

Vaishnavi

354,971 просмотров • 4 месяцев назад

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!
1:10

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 🚀

45,256 просмотров • 5 месяцев назад