Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

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...

reach_vb's profile picture

Vaibhav (VB) Srivastav

47,375 subscribers

93,512 Aufrufe • vor 11 Monaten •via X (Twitter)

Wissenschaft & TechnologieNachrichten & PolitikBildung
LIVE

Anya Rossi• Live Now

Private livecam show

6 Kommentare

Profilbild von Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastavvor 11 Monaten

Check out their models here:

Profilbild von Aakash
Aakashvor 11 Monaten

"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

Profilbild von KD
KDvor 11 Monaten

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

Profilbild von ZAZO
ZAZOvor 11 Monaten

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

Profilbild von Bui Dinh Ngoc
Bui Dinh Ngocvor 11 Monaten

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.

Profilbild von Carlos DP
Carlos DPvor 11 Monaten

SUCH a solid demo lol, S tier

Ähnliche 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:
1:12

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

171,391 Aufrufe • vor 11 Monaten

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) 🏋️‍♂️
1:23

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

228,836 Aufrufe • vor 1 Jahr

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! 🤗
1:48

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

45,606 Aufrufe • vor 1 Jahr

🚨 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!
1:12

🚨 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

47,183 Aufrufe • vor 1 Jahr

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 🤗
1:08

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

66,963 Aufrufe • vor 1 Jahr

NEW: Kokoro 82M - APACHE 2.0 licensed, Text to Speech model, trained on < 100 hours of audio 🔥
1:54

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

Vaibhav (VB) Srivastav

330,034 Aufrufe • vor 1 Jahr

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:
0:53

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

66,264 Aufrufe • vor 1 Jahr

"With the On-Demand model, users can choose their gas cost with the lowest latency possible for their transactions" - DoctorBlocks Listen to what DoctorBlocks says about functions and the importance of Switchboard's On-Demand model 👇
1:02

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

Switchboard ⚡️

40,645 Aufrufe • vor 2 Jahren

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⬇️
0:51

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

196,152 Aufrufe • vor 1 Jahr

🚨 Official : Google will soon release Gemini 2.5 Flash - Low latency model and most cost-efficient - Has "thinking built-in" - Allows users to control how much the model reasons. Source : YT Google Cloud Keynote.
0:37

🚨 Official : Google will soon release Gemini 2.5 Flash - Low latency model and most cost-efficient - Has "thinking built-in" - Allows users to control how much the model reasons. Source : YT Google Cloud Keynote.

AshutoshShrivastava

60,315 Aufrufe • vor 1 Jahr

Pretty Insane - SoTA Text to Speech model capable of English AND Hindi - 3B Llama backbone - Apache 2.0 licensed 🔥 > Sub 80 ms latency > Supports both English, Hindi including code-mix > Runs in a free google colab too 🤯 Best part: They're actively working on other languages like Tamil, Telugu, Bengali, etc > Available on Hugging Face hub, powered by Transformers 💥
0:52

Pretty Insane - SoTA Text to Speech model capable of English AND Hindi - 3B Llama backbone - Apache 2.0 licensed 🔥 > Sub 80 ms latency > Supports both English, Hindi including code-mix > Runs in a free google colab too 🤯 Best part: They're actively working on other languages like Tamil, Telugu, Bengali, etc > Available on Hugging Face hub, powered by Transformers 💥

Vaibhav (VB) Srivastav

33,749 Aufrufe • vor 11 Monaten

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! 🐐
0:36

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

47,921 Aufrufe • vor 1 Jahr

🔊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
1:21

🔊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

935,674 Aufrufe • vor 2 Monaten

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!
0:27

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

43,620 Aufrufe • vor 1 Jahr

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.
0:30

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

335,344 Aufrufe • vor 2 Jahren

This is the best and fastest speech-to-text model in the world: • 23.2 seconds to process 30 minutes of audio • 93.3% accuracy • Diarization support to detect multiple speakers • Trained on 12.5 million hours of multilingual data I tried it out and it's pretty impressive:
3:20

This is the best and fastest speech-to-text model in the world: • 23.2 seconds to process 30 minutes of audio • 93.3% accuracy • Diarization support to detect multiple speakers • Trained on 12.5 million hours of multilingual data I tried it out and it's pretty impressive:

Santiago

66,397 Aufrufe • vor 9 Monaten

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!
0:37

Really proud to share something we’ve been working on for a while: Magenta RealTime 2 (MTR2), a live music model that is highly interactive (MIDI, audio, text, lots of parameters) and low-latency (~200ms end-to-end), and runs locally on a MacBook!

Ilaria Manco

44,003 Aufrufe • vor 15 Tagen

Gemma 2 2B running in a browser, powered by WebLLM &amp; WebGPU! 🔥 100% local &amp; on-device In less than 24 hours, we've already got the model to the edge! ⚡ Try it out on an HF space below:
1:31

Gemma 2 2B running in a browser, powered by WebLLM &amp; WebGPU! 🔥 100% local &amp; on-device In less than 24 hours, we've already got the model to the edge! ⚡ Try it out on an HF space below:

Vaibhav (VB) Srivastav

53,790 Aufrufe • vor 1 Jahr