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.

Introducing Faster Qwen3TTS! Realistic voice generation at 4x real time: - Same amazing voice quality from Qwen's model - Streaming support with <200 ms to first audio - 5x faster than the official implementation Just pip install faster-qwen3-tts Try the demo!

Andi Marafioti

7,693 subscribers

92,497 views • 6 months ago •via X (Twitter)

Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Introducing MiniMax FastH3 on Reactor - the latest open-source model by MiniMax (official). Stream 720p with audio at $0.007/second with first frame image support, faster and cheaper than ever. Get started now by cloning our demo app:

Introducing MiniMax FastH3 on Reactor - the latest open-source model by MiniMax (official). Stream 720p with audio at $0.007/second with first frame image support, faster and cheaper than ever. Get started now by cloning our demo app:

reactor

536,720 views • 1 day ago

just wrapped up the PBR path tracer for my engine, and looks like it's about 5x faster than Unreal Engine and 12x faster than Unity for the same scene. goal is to make this real time

just wrapped up the PBR path tracer for my engine, and looks like it's about 5x faster than Unreal Engine and 12x faster than Unity for the same scene. goal is to make this real time

Gabriel Dechichi

79,337 views • 6 months ago

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

662,286 views • 24 days 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

14,328 views • 28 days ago

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:

ElevenLabs just lost the crown - to open source. Chatterbox by Resemble AI (I remember writing about this team back in 2022 as a pioneer of AI audio) just released as an open-source alternative for audio generation and voice cloning. - Zero-shot voice cloning from just 5 seconds of audio - Unique emotion intensity control—from subtle to dramatically expressive - Real-time voice synthesis faster than real-time inference - Built-in watermarking for secure, trusted audio - Consistently preferred over ElevenLabs in blind evaluations Fully open-source. No hidden restrictions. This is the way. Check out the demo:

AI Breakfast

454,451 views • 1 year ago

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

OpenAI just announced "GPT-4o". It can reason with voice, vision, and text. The model is 2x faster, 50% cheaper, and has 5x higher rate limit than GPT-4 Turbo. It will be available for free users and via the API. The voice model can even pick up on emotion and generate emotive voice.

Lior Alexander

485,137 views • 2 years ago

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season

Don't waste time choosing between models Introducing Multiple Model Generation: → Test up to 4 models at once → Same prompt. Same settings. Side by side → Find what works best for you, faster Time to pick the diamond of the season

Magnific

34,374 views • 7 months ago

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.

Introducing our new Turbo 2.5 model - Hindi, French, Spanish, Mandarin and 27 other languages just got 3x faster. This unlocks high-quality low-latency conversational AI for nearly 80% of the world. For the first time, we support Vietnamese, Hungarian and Norwegian text to speech. And English is now 25% faster compared to Turbo v2.

ElevenLabs

50,875 views • 2 years ago

BREAKING: voice AI just had its ChatGPT moment Cartesia's Sonic 3 is the first production-ready TTS that laughs naturally, speaks 42 languages, and responds faster than you can notice. 100K free credits up for grabs rn Here's what makes it amazing (with demos):

BREAKING: voice AI just had its ChatGPT moment Cartesia's Sonic 3 is the first production-ready TTS that laughs naturally, speaks 42 languages, and responds faster than you can notice. 100K free credits up for grabs rn Here's what makes it amazing (with demos):

Robin Delta

115,809 views • 10 months ago

🤯Real-time video generation just got HUGE. Introducing Helios: A 14B parameter model running at 19.5 FPS on a single H100. Cheaper, Faster, and Stronger than 1.3B models, generating minute-long videos without the usual tricks (even no quantization).

🤯Real-time video generation just got HUGE. Introducing Helios: A 14B parameter model running at 19.5 FPS on a single H100. Cheaper, Faster, and Stronger than 1.3B models, generating minute-long videos without the usual tricks (even no quantization).

Bin Lin

27,761 views • 6 months ago

It's official — Wispr Flow is now live on the iPhone App Store! We built the first immersive voice keyboard that lets you dictate with incredible accuracy anywhere — 5x faster than typing. Delightful. Effortless. Intelligent. Our mission is to change how people interact with technology and move people from display-first to voice-first interfaces. This product gets us one step closer to empowering people's voices wherever they are.

It's official — Wispr Flow is now live on the iPhone App Store! We built the first immersive voice keyboard that lets you dictate with incredible accuracy anywhere — 5x faster than typing. Delightful. Effortless. Intelligent. Our mission is to change how people interact with technology and move people from display-first to voice-first interfaces. This product gets us one step closer to empowering people's voices wherever they are.

Wispr Flow

130,173 views • 1 year ago

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Introducing Oasis: the first playable AI-generated game. We partnered with Decart to build a real-time, interactive world model that runs >10x faster on Sohu. We're open-sourcing the model architecture, weights, and research. Here's how it works (and a demo you can play!):

Etched

24,714,738 views • 1 year ago

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

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

Charly Wargnier

59,144 views • 7 months ago

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Voice agents are awkward, and everyone notices: You ask a question. The agent thinks. You wait. And wait... Nobody wants this. I'd rather talk to a person. If your model's response time is over 300ms, you won't make it. Unfortunately, most text-to-speech models can't get anywhere close to that. I want you to take a look at the latest model released by Inworld AI: TTS-1.5. I built a simple voice agent using the model so you can see it in action and test it on your computer. You'll find the repository link below. The latency numbers of this model are wild: • Max model → under 250ms • Mini model → under 130ms That's 4x faster than prior generations and faster than human response times!

Santiago

69,455 views • 7 months ago

With Astra, ChatGPT is nearly 2x faster at computer use than before. In addition to the amazing new model, we’ve optimized the harness to make computer use run much faster. These optimizations work in existing models too, so tasks are sped up by ~60% in GPT-5.6 Sol. Try it!

With Astra, ChatGPT is nearly 2x faster at computer use than before. In addition to the amazing new model, we’ve optimized the harness to make computer use run much faster. These optimizations work in existing models too, so tasks are sped up by ~60% in GPT-5.6 Sol. Try it!

Ari Weinstein

225,508 views • 19 hours ago

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.

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 views • 5 months ago

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

This is the DeepSeek moment for Voice AI. Chatterbox Turbo is an MIT-licensed voice model that beats ElevenLabs Turbo & Cartesia Sonic 3! - <150ms time-to-first-sound - Voice cloning from just 5-second audio - Paralinguistic tags for real human expression 100% open-source.

Akshay 🚀

468,788 views • 8 months ago

Introducing Muranyi 3. The world’s most powerful AI model to make games. Ideas to games, faster than ever. Built with improved graphics and VFX, smoother animations, advanced game logic, smarter NPC behavior, faster loading times, faster generation, and more reliable builds. A new way to build worlds, dream up games, and bring them to life. Publish instantly. Earn from day one. You imagined it. Now build it.

Introducing Muranyi 3. The world’s most powerful AI model to make games. Ideas to games, faster than ever. Built with improved graphics and VFX, smoother animations, advanced game logic, smarter NPC behavior, faster loading times, faster generation, and more reliable builds. A new way to build worlds, dream up games, and bring them to life. Publish instantly. Earn from day one. You imagined it. Now build it.

Tesana - Make games with AI

123,265 views • 3 months ago