Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Kyutai released their Streaming Text to Speech model, ~2B param model, ultra low latency (220ms), CC-BY-4.0 license 🔥 Trained on 2.5 Million Hours of audio, it can serve up to 32 users w/ less than 350ms latency on a SINGLE L40 🤯 Incredible release by kyutai folks, go check... show more

Vaibhav (VB) Srivastav

55,570 subscribers

93,586 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics Education

Anya Rossi• Live Now

Private livecam show

6 Comments

Vaibhav (VB) Srivastav1 year ago

Check out their models here:

Aakash1 year ago

"Trained on 2.5 Million Hours of audio, it can serve up to 32 users w/ less than 350ms latency on a SINGLE L40" can we get more of this benchmark

KD1 year ago

These are some of the same guys who run a really amazing YT channel about CS btw:

ZAZO1 year ago

that’s the best thing happened in 2025 🔥🔥🔥🔥🔥🔥🔥🔥🔥

Bui Dinh Ngoc1 year ago

This is game-changing for accessibility tools. I've been waiting for low-latency TTS that doesn't break the bank or require proprietary licenses.

Carlos DP1 year ago

SUCH a solid demo lol, S tier

Related Videos

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:

Kyutai TTS and Unmute are now open source! The text-to-speech is natural, customizable, and fast: it can serve 32 users with a 350ms latency on a single L40S. Try it out and get started on the project page:

kyutai

174,129 views • 1 year ago

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

LETS GOOO! FishSpeech v1.5 - multilingual, zero-shot instant voice cloning, low-latency, open text to speech model 🔥 > Only 500M params > Trained on 1 MILLION hours of audio > Supports 13 languages > Low-latency ( Open model - checkpoints on the hub 🤗 > Best part: Ranks #2 on TTS Arena (preliminary results) Kudos to Fish Audio - truly leading the way for open text to speech research! ⚡

Vaibhav (VB) Srivastav

49,169 views • 1 year ago

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

The new open-source Text to Speech model: Fish Speech 1.4 is brilliant! Trained on a massive 700K hours of multilingual speech data in 8 languages - Instant voice cloning 🗣️ - Ultra-low latency ⚡ - Compact model (~1GB weights) 🏋️‍♂️

Rohan Paul

228,905 views • 2 years ago

LETS GOO! kyutai just released MoshiVis - an end-to-end low-latency Vision Speech Model, CC-BY license 🔥 > Only adds 206M parameters via lightweight cross-attention (CA) modules to integrate visual inputs from a frozen PaliGemma2-3B-448 vision encoder > Uses a learnable gating mechanism in the CA modules allows MoshiVis to "turn off" visual input streams when unnecessary, preserving Moshi's conversational abilities > Adds only ~7ms per inference step on a MacMini with M4 Pro Chip, maintaining real-time performance > Best part: it keeps the tone, emotion and the prosody of the original Moshi model > CC-BY-4.0 licensed weights on the hub, allows commercial use > Works with MLX, Candle and PyTorch from day-0 Kudos Kyutai on such a brilliant release - I believe this is the first of its kind! 🤗

LETS GOO! kyutai just released MoshiVis - an end-to-end low-latency Vision Speech Model, CC-BY license 🔥 > Only adds 206M parameters via lightweight cross-attention (CA) modules to integrate visual inputs from a frozen PaliGemma2-3B-448 vision encoder > Uses a learnable gating mechanism in the CA modules allows MoshiVis to "turn off" visual input streams when unnecessary, preserving Moshi's conversational abilities > Adds only ~7ms per inference step on a MacMini with M4 Pro Chip, maintaining real-time performance > Best part: it keeps the tone, emotion and the prosody of the original Moshi model > CC-BY-4.0 licensed weights on the hub, allows commercial use > Works with MLX, Candle and PyTorch from day-0 Kudos Kyutai on such a brilliant release - I believe this is the first of its kind! 🤗

Vaibhav (VB) Srivastav

46,585 views • 1 year ago

The Moshi speech-to-speech model by kyutai, hosted on Modal, absolutely cranks! Near instantaneous voice chat AI, thanks to bidirectional streaming. Whole startups could be built on this stack.

The Moshi speech-to-speech model by kyutai, hosted on Modal, absolutely cranks! Near instantaneous voice chat AI, thanks to bidirectional streaming. Whole startups could be built on this stack.

Erik Dunteman

55,420 views • 2 years ago

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!

🚨 New model alert! Dialog by vibx — a leading text-to-speech model — now runs on GroqCloud™. That means natural-sounding speech with ultra-low latency, making real-time voice applications smoother and more responsive. Learn more & build fast — links in the comments!

Groq Inc

47,474 views • 1 year ago

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗

Wow! New Speech to Speech model - Fish Agent v0.1 3B by Fish Audio 🔥 > Trained on 700K hours of multilingual audio > Continue-pretrained version of Qwen-2.5-3B-Instruct for 200B audio & text tokens > Zero-shot voice cloning > Text + audio input/ Audio output > Ultra-fast inference w/ 200ms TTFA > Models on the Hub & Finetuning code on its way! 🚀 What an amazing time to be alive 🤗

Vaibhav (VB) Srivastav

67,003 views • 2 years ago

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥

Vaibhav (VB) Srivastav

330,034 views • 1 year ago

aaaannd it plays Doom now. On device, 150ms latency, on 1B param model

aaaannd it plays Doom now. On device, 150ms latency, on 1B param model

Harsha Gundala

102,882 views • 1 month ago

Kyutai Speech-To-Text is now open-source! It’s streaming, supports batched inference, and runs blazingly fast: perfect for interactive applications. Check out the details here:

Kyutai Speech-To-Text is now open-source! It’s streaming, supports batched inference, and runs blazingly fast: perfect for interactive applications. Check out the details here:

kyutai

67,041 views • 1 year ago

You don't need a GPU to run text-to-speech anymore. Kyutai released Pocket TTS, a 100 million parameter speech model that runs entirely on CPU. How it performs: > Nearly 6x faster than real time on a MacBook CPU > First audio chunk arrives in about 200 milliseconds > Runs on just 2 CPU cores > Supports voice cloning and 6 languages Setup takes one command: pip install pocket-tts Text-to-speech that used to need a GPU or a paid API now runs locally, on a laptop, in near real time.

You don't need a GPU to run text-to-speech anymore. Kyutai released Pocket TTS, a 100 million parameter speech model that runs entirely on CPU. How it performs: > Nearly 6x faster than real time on a MacBook CPU > First audio chunk arrives in about 200 milliseconds > Runs on just 2 CPU cores > Supports voice cloning and 6 languages Setup takes one command: pip install pocket-tts Text-to-speech that used to need a GPU or a paid API now runs locally, on a laptop, in near real time.

Simplifying AI

14,498 views • 3 months ago

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️

PlayAI

196,375 views • 1 year ago

"With the On-Demand model, users can choose their gas cost with the lowest latency possible for their transactions" - Dr Blocks Listen to what Dr Blocks says about functions and the importance of Switchboard's On-Demand model 👇

"With the On-Demand model, users can choose their gas cost with the lowest latency possible for their transactions" - Dr Blocks Listen to what Dr Blocks says about functions and the importance of Switchboard's On-Demand model 👇

Switchboard ⚡️

40,794 views • 2 years ago

End to End Speech models are on fire - LLAMA-OMNI 8B - Apache licensed! 🔥 > Speech Encoder - Whisper Large v3 > LLM backbone - Llama 3.1 8B Instruct > Speech Decoder - HuBERT (UnitY) > Simultaneously generate Speech + Text > Less than 250 ms latency > Trained in less than 3 days on 4x GPUs > Used 200K instruct pairs > Model checkpoints on the Hub 🤗 > Space incoming! GG! I'm here for this trend! 🐐

End to End Speech models are on fire - LLAMA-OMNI 8B - Apache licensed! 🔥 > Speech Encoder - Whisper Large v3 > LLM backbone - Llama 3.1 8B Instruct > Speech Decoder - HuBERT (UnitY) > Simultaneously generate Speech + Text > Less than 250 ms latency > Trained in less than 3 days on 4x GPUs > Used 200K instruct pairs > Model checkpoints on the Hub 🤗 > Space incoming! GG! I'm here for this trend! 🐐

Vaibhav (VB) Srivastav

47,943 views • 2 years ago

Just released on Hugging Face: Vui, a 100M open-source NotebookLM! 3 models: > Vui.BASE is the base checkpoint trained on 40k hours of audio conversations > Vui.ABRAHAM is a single speaker model that can reply with context awareness. > Vui.COHOST is checkpoint with two speakers that can talk to each other. It clones voices, breathes, uhs, [laughs] — even non-speech sounds. Human-like TTS is here!

Just released on Hugging Face: Vui, a 100M open-source NotebookLM! 3 models: > Vui.BASE is the base checkpoint trained on 40k hours of audio conversations > Vui.ABRAHAM is a single speaker model that can reply with context awareness. > Vui.COHOST is checkpoint with two speakers that can talk to each other. It clones voices, breathes, uhs, [laughs] — even non-speech sounds. Human-like TTS is here!

steven

43,661 views • 1 year ago

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

Mistral AI

953,789 views • 7 months ago

Here's our new, tiniest model: LFM2.5-230M! 🥳 We went even smaller to power ultra-low latency use cases like e-commerce and robotics. Here's a demo of LFM2.5-230M running on a Unitree G1, decomposing user prompts into a sequence of tool calls. Available today on Hugging Face!

Here's our new, tiniest model: LFM2.5-230M! 🥳 We went even smaller to power ultra-low latency use cases like e-commerce and robotics. Here's a demo of LFM2.5-230M running on a Unitree G1, decomposing user prompts into a sequence of tool calls. Available today on Hugging Face!

Maxime Labonne

25,366 views • 4 months ago

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.

Alvaro Cintas

335,391 views • 3 years ago