Загрузка видео...

Не удалось загрузить видео

На главную

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built...

kamath_sutra's profile picture

Sudarshan Kamath

21,655 subscribers

71,298 просмотров • 4 месяцев назад •via X (Twitter)

ОбразованиеНовости и политикаНаука и технологии
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗
2:10

NEW: Higgs Audio V2 from BosonAI open, unified TTS model w/ voice cloning, beats GPT 4o mini tts and ElevenLabs v2 🔥 > Trained on 10M hours (speech, music, events) > Built on top of Llama 3.2 3B > Works real-time and on edge > Beats GPT-4o-mini-tts, ElevenLabs v2 in prosody & emotion Multi-speaker dialog > Zero-shot voice cloning 🤩 > Available on Hugging Face Kudos to folks at Boson AI for releasing such a brilliant work and all the details around the model! 🤗

Vaibhav (VB) Srivastav

79,585 просмотров • 1 год назад

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?
3:29

I built a service desk agent using ElevenLabs’ new Conversational AI Agents feature. Watch the video to see how responsive it is! Previously, I used ElevenLabs for cloning my voice and used my generated voice for narrations in some of my youtube videos. This feature takes elevenlabs' voice AI to a whole new level! It simplifies systems that used to require separate TTS (text-to-speech) and STT (speech-to-text) processes for both sides of the conversation. Now, it’s much simpler! Create your own agent here What will you create with this?

Melvin Vivas

27,722 просмотров • 1 год назад

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)
0:52

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)

rumik

26,553 просмотров • 19 дней 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 • 6 месяцев назад

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.
0:27

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

Vaibhav Sisinty

24,531,575 просмотров • 3 месяцев назад

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:
2:41

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 просмотров • 1 год назад

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was *especially* amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!
2:13

I joined OpenAI at the beginning of the year -- partly because I was excited about the possibility of better voice interaction with computers. So it was *especially* amazing to work with the team here on the gpt-4o model launch. It's hard to grok until you try it how big of a step forward this is for human/computer voice communication. It feels different -- it's obvious that the model understands you better than anything you've used before. This is my favorite demo of gpt-4o, it demonstrates not just good stt/tts, but actual conversational ability over full, realistic phone call. It's so obvious how useful this will be!

Peter Bakkum

144,441 просмотров • 2 лет назад

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:
3:38

This is the fastest text-to-speech and speech-to-text API out there. It's under 250 ms to first-byte latency. That's what we need to deploy conversational AI applications everywhere! (I can't wait for the death of automated voice machines.) Look at the attached video. For the first time, I could have a conversation with an AI agent in real time without awkward pauses. This technology is Aura from Deepgram. It's the fastest text-to-speech option I've seen. Here is a GitHub repository with the demo in the video: You can use it to build a conversational AI application using natural voice. You'll need a Deepgram API Key and an OpenAI API Key. Thanks to Deepgram for giving me access to Aura and collaborating with me on this post. If you want to learn more about Aura, here is the announcement post:

Santiago

185,560 просмотров • 2 лет 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 🔥

Charly Wargnier

565,251 просмотров • 6 месяцев назад

🚀 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
1:26

🚀 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 просмотров • 3 месяцев назад

What if you could talk to your Telegram bot and it actually talked back? Learn how built a voice-enabled Telegram bot with the Gemini Interactions API in ~400 lines of Python. Send a voice note in any language, Gemini understands the audio and replies with text and a spoken voice message. Uses: - Gemini 3.1 Flash Lite for reasoning, 3.1 Flash TTS for speech - Interactions API handles multi-turn memory server-side - Native audio input, no transcription step needed - Deploys to Cloud Run with scale-to-zero Awesome work by Thor 雷神 ⚡️. 🤗
9:11

What if you could talk to your Telegram bot and it actually talked back? Learn how built a voice-enabled Telegram bot with the Gemini Interactions API in ~400 lines of Python. Send a voice note in any language, Gemini understands the audio and replies with text and a spoken voice message. Uses: - Gemini 3.1 Flash Lite for reasoning, 3.1 Flash TTS for speech - Interactions API handles multi-turn memory server-side - Native audio input, no transcription step needed - Deploys to Cloud Run with scale-to-zero Awesome work by Thor 雷神 ⚡️. 🤗

Philipp Schmid

11,156 просмотров • 3 месяцев назад

Today we are launching a new model powering Cartesia's Voice Changer – the ultimate tool to transform, clone, and localize voices. 🎭 Fine-tune every detail - Adjust pacing, expressiveness, inflections, and more to get the perfect delivery. 🗣 Leverage our voice library - Pick from a wide range of high-quality AI voices to fit any mood or style, across 15 languages and numerous dialects. 🔬 Custom voice cloning - Create a unique AI voice and use it seamlessly with our voice changer. 🌍 Next-level localization - Translate while keeping original tone & emotions intact. Try out our voice changer in our Playground 👇. Check out some fun examples in the 🧵 and share what you make!
0:24

Today we are launching a new model powering Cartesia's Voice Changer – the ultimate tool to transform, clone, and localize voices. 🎭 Fine-tune every detail - Adjust pacing, expressiveness, inflections, and more to get the perfect delivery. 🗣 Leverage our voice library - Pick from a wide range of high-quality AI voices to fit any mood or style, across 15 languages and numerous dialects. 🔬 Custom voice cloning - Create a unique AI voice and use it seamlessly with our voice changer. 🌍 Next-level localization - Translate while keeping original tone & emotions intact. Try out our voice changer in our Playground 👇. Check out some fun examples in the 🧵 and share what you make!

Cartesia

11,324 просмотров • 1 год назад

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇
8:20

VoiceBox just did what everyone thought was impossible. It might have killed ElevenLabs overnight. No subscription. No cloud. No credits. Runs locally on your machine. Clones a voice from 3 seconds of audio. Powered by Qwen 3 TTS. Apache 2.0 license. Commercial use allowed. And your voice data never leaves your computer. For years, if you wanted high quality voice cloning, ElevenLabs was the default. Now there’s a free open-source alternative that sounds shockingly close. Plus it has a built-in multi-track editor, recording, transcription with Whisper, and a local API. This isn’t just another TTS tool. It’s a full voice production studio on your desktop. Open source AI is catching up fast. And this changes the game for creators and businesses. Would you trust the cloud with your voice… or keep it local? 👇

Julian Goldie SEO

59,167 просмотров • 5 месяцев назад

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.
4:35

A voice agent powered by gpt-oss. Running locally on my macBook. Demo recorded in a Waymo with WiFi turned off. I'm still on my space game voice AI kick, obviously. Code link below. For conversational voice AI, you want to set the gpt-oss reasoning behavior to "low". (The default is "medium".) Notes on how to do that and a jinja template you can use are in the repo. The LLM in the demo video is the big, 120B version of gpt-oss. You can use the smaller, 20B model for this, of course. But OpenAI really did a cool thing here designing the 120B model to run in "just" 80GB of VRAM. And the llama.cpp mlx inference is fast: ~250ms TTFT. Running a big model on-device feels like a time warp into the future of AI.

kwindla

202,147 просмотров • 11 месяцев назад

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.
1:21

Mistral just released Voxtral TTS, an open-weight voice model that tries to match ElevenLabs while keeping it free. A 3-billionn param model that fits on a laptop and runs 6X faster than real-time speech. It is split into 3 parts that handle different jobs. - The 3.4B part is the main language brain that understands the text and plans what should be spoken. - The 390M part turns that plan into speech features like rhythm, pronunciation, and tone. - The 300M part converts those speech features into the final compressed audio signal you can play. That split helps because each part only does the job it is best at, which can make the whole system faster and lighter than one giant model doing everything alone. Mistral claims about 90ms to first audio, about 6x faster than real-time speech output, about 3GB RAM after quantization, 9 languages, and voice copying from 5s of audio, even across languages. Its internal tests report 62.8% preference over ElevenLabs Flash on default voices and 69.9% on custom voices, but the bigger point is that companies can keep speech data on their own machines. IMO, enterprise buyers usually care most about control, cost, and latency, So this model should give it great push for voice-based AI apps/products.

Rohan Paul

15,672 просмотров • 4 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 • 5 месяцев назад

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs
1:09

Mati Staniszewski on why ElevenLabs is betting on a cascaded approach for voice agents: “Our approach, as you think about voice agents, conversational agents, is effectively a cascaded approach. You use transcription or speech-to-text, an LLM, text-to-speech, and orchestrate all of that together. Then you have speech-to-speech, which goes directly from speech, and there’s a speech response on the other side. Today, we are optimizing heavily on a cascaded approach. As we work with a lot of the businesses and enterprises, they will need that visibility into what happens. They will want to execute certain tasks on top of that. They want good visibility into each of the steps and great accuracy of all the models. But beyond that, they can abstract away what’s the LLM layer, what’s the intelligence layer, and the integrations are easier in that system. That’s where we are betting a lot of the research work on how you can make that great, and we think we can make that great.” John Collison Mati Staniszewski ElevenLabs

Stripe

17,118 просмотров • 3 месяцев назад

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.
1:58

VoxCPM 2 just dropped by OpenBMB Only 2B-param open-source TTS (Text-to-Speech) model built for production-grade multilingual voice work. Apache-2.0 license, Can run on only 8GB VRAM. • Eliminates the "robotic" feel of traditional TTS, delivering prosody and emotional depth suitable for high-stakes professional environments like filmmaking, gaming, animation, and audiobooks. • 30-language multilingual: no language tag needed, just type in a supported language and generate directly. • Voice design: create a brand-new voice from a text description alone, like age, tone, pace, or emotion. No reference audio required. Describe the desired voice characteristics (gender, age, tone, emotion, pace …) in Control Instruction, and VoxCPM2 will craft a unique voice from your description alone. • Controllable cloning: clone from a short clip, then steer delivery style without losing the speaker’s core voice. • Ultimate cloning: use reference audio + transcript for continuation-style cloning that keeps the tiny vocal details. • 48kHz output: takes 16kHz reference audio and produces studio-quality speech without an external upsampler. • Real-time ready: around 0.3 RTF on RTX 4090, even lower with Nano-VLLM. • Commercial use: Apache-2.0 licensed. Developer-Friendly Infrastructure: - Native Torch Inference: Direct support for PyTorch-based workflows. - Training Flexibility: Supports both full-parameter and LoRA fine-tuning for specific domain adaptation. - Production Readiness: Compatible with voxcpm-nanovllm for large-scale, high-concurrency deployment.

Rohan Paul

13,541 просмотров • 3 месяцев 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

54,912 просмотров • 2 месяцев назад

Did Google just mass-murdered every voice AI startup irrelevant? Google just shipped Gemini 3.1 Flash Live. Real-time voice AND vision. Sub-second latency. 90+ languages. And the one thing no voice AI has cracked until now: it filters background noise in real-world environments. Not demo environments. Real ones. Traffic outside. TV left on. Drill running next door. That's the wall every voice AI startup has been quietly hitting for three years. The demos worked. The deployments didn't. Because the real world is loud and messy and the models couldn't tell your voice from the noise around it. Google just called that problem solved. And it's not sitting in a research paper. It's already running in production apps. Stitch is using it to let designers talk to their canvas in real-time. Ato is using it to give elderly people a companion who actually listens. Wit's End built an RPG game master with it that delivers theatrical dialogue indistinguishable from a human voice actor. Three live products. Three different industries. All shipping now. Every voice AI startup just woke up to a new baseline. The question isn't whether to build with this. The question is how fast.
0:57

Did Google just mass-murdered every voice AI startup irrelevant? Google just shipped Gemini 3.1 Flash Live. Real-time voice AND vision. Sub-second latency. 90+ languages. And the one thing no voice AI has cracked until now: it filters background noise in real-world environments. Not demo environments. Real ones. Traffic outside. TV left on. Drill running next door. That's the wall every voice AI startup has been quietly hitting for three years. The demos worked. The deployments didn't. Because the real world is loud and messy and the models couldn't tell your voice from the noise around it. Google just called that problem solved. And it's not sitting in a research paper. It's already running in production apps. Stitch is using it to let designers talk to their canvas in real-time. Ato is using it to give elderly people a companion who actually listens. Wit's End built an RPG game master with it that delivers theatrical dialogue indistinguishable from a human voice actor. Three live products. Three different industries. All shipping now. Every voice AI startup just woke up to a new baseline. The question isn't whether to build with this. The question is how fast.

Vaibhav Sisinty

59,339 просмотров • 4 месяцев назад