Loading video...

Video Failed to Load

Go Home

Today, we released Gemini 3.5 Live Translate, our latest audio model for live speech-to-speech translation. It supports over 70 languages and starts translating as soon as you start talking, streaming translations while listening to what you say next. No awkward pauses or choppy audio, just real connection without language...

GoogleAI's profile picture

Google AI

2,443,182 subscribers

3,986,044 views • 2 months ago •via X (Twitter)

Health & WellnessScience & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps. Here’s an example of how partners at Grab are helping connect travelers with drivers. 🚗 Rolling out in Google Translate and via the Live API in Google AI Studio.
0:48

Speech translation has been one of the longest-running ML efforts at Google, and we’ve come a long way. Gemini 3.5 Live Translate is our latest speech-to-speech model, supporting 70+ languages. It enables more natural conversations across languages in everyday products and apps. Here’s an example of how partners at Grab are helping connect travelers with drivers. 🚗 Rolling out in Google Translate and via the Live API in Google AI Studio.

Jeff Dean

35,828 views • 2 months ago

Gemini 3.5 Live Translate! We just shipped a real-time babel fish. - 70+ languages, 2,000+ language pairs. - Natural translated speech, works in noisy environments. - Stays in sync with the speaker, no lag, no awkward pauses. - Auto-detects the language being spoken. Available today in Google Translate (Android & iOS), the Gemini API (Public Preview), and Google Meet (Private Preview). I genuinely think this is the beginning of the end of language barriers. Anyone can now speak and understand anyone.
1:33

Gemini 3.5 Live Translate! We just shipped a real-time babel fish. - 70+ languages, 2,000+ language pairs. - Natural translated speech, works in noisy environments. - Stays in sync with the speaker, no lag, no awkward pauses. - Auto-detects the language being spoken. Available today in Google Translate (Android & iOS), the Gemini API (Public Preview), and Google Meet (Private Preview). I genuinely think this is the beginning of the end of language barriers. Anyone can now speak and understand anyone.

Philipp Schmid

17,485 views • 2 months ago

Add near real-time voice translation to your apps with Gemini 3.5 Live Translate via the Gemini Live API. 🎙️ Watch how the model handles live broadcast ingestion and translation with continuous speech-to-speech streaming (S2ST) and synced transcripts, letting users tune into global radio broadcasts in their native language.
0:43

Add near real-time voice translation to your apps with Gemini 3.5 Live Translate via the Gemini Live API. 🎙️ Watch how the model handles live broadcast ingestion and translation with continuous speech-to-speech streaming (S2ST) and synced transcripts, letting users tune into global radio broadcasts in their native language.

Google AI Developers

3,544,749 views • 2 months ago

What will you build this weekend? 🛠️ Gemini 3.5 Live Translate is officially in Preview via the Gemini Live API and Google AI Studio! Skip the fragmented multi-model stack. Stream audio in,get translated audio out. 👇Tap the link to try it out in Google AI Studio: Start building apps:
0:30

What will you build this weekend? 🛠️ Gemini 3.5 Live Translate is officially in Preview via the Gemini Live API and Google AI Studio! Skip the fragmented multi-model stack. Stream audio in,get translated audio out. 👇Tap the link to try it out in Google AI Studio: Start building apps:

Google for Developers

13,394 views • 2 months ago

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations
2:50

Listen up 🔊 We’ve made some updates to our Gemini Audio models and capabilities: — Gemini’s live speech-to-speech translation capability is rolling out in a beta experience to the Google Translate app, bringing you real-time audio translation that captures the nuance of human speech — Gemini 2.5 Flash and 2.5 Pro Text-to-Speech preview models bring improved adherence to style prompts, precision pacing with context-aware speed adjustments, and character voice consistency for multi-speaker scenarios — Gemini 2.5 Flash Native Audio is now updated, with improvements to handle complex workflows, navigate user instructions, and hold natural conversations

Google AI

1,093,819 views • 8 months ago

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output! The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓
1:14

Today we launched Gemini 3.1 Flash TTS, our most expressive and controllable text-to-speech model yet. This launch [excitement] includes audio tags! 🗣🏷 Audio tags [explanatory] are a seamless way to guide vocal style, pace, and delivery using natural language commands embedded directly in your text. Want a different tempo or tone? [amazement] Just tag the audio to steer the AI-speech output! The model supports 70+ languages (24 of which are high-quality evaluated languages, including: Japanese, Hindi, and Arabic). Watch the audio tags in action in the demo below ↓

Google AI

203,166 views • 4 months ago

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.
4:10

Google presents AudioPaLM: A Large Language Model That Can Speak and Listen paper page: introduce AudioPaLM, a large language model for speech understanding and generation. AudioPaLM fuses text-based and speech-based language models, PaLM-2 [Anil et al., 2023] and AudioLM [Borsos et al., 2022], into a unified multimodal architecture that can process and generate text and speech with applications including speech recognition and speech-to-speech translation. AudioPaLM inherits the capability to preserve paralinguistic information such as speaker identity and intonation from AudioLM and the linguistic knowledge present only in text large language models such as PaLM-2. We demonstrate that initializing AudioPaLM with the weights of a text-only large language model improves speech processing, successfully leveraging the larger quantity of text training data used in pretraining to assist with the speech tasks. The resulting model significantly outperforms existing systems for speech translation tasks and has the ability to perform zero-shot speech-to-text translation for many languages for which input/target language combinations were not seen in training. AudioPaLM also demonstrates features of audio language models, such as transferring a voice across languages based on a short spoken prompt.

AK

290,517 views • 3 years ago

We will have around 2.5 hours of Chinese speech and and around half hour for different languages speakers. ( Most English). So please download your translator on your phone. I use Google translate voice translate. Or if you have a better one that will be great! If you can't join in or you can't understand, you can just listen to feel the energy. We are sorry we can't translate to English when we are in the meeting because there is too much information. We will translate to English soon after the conference. And you can translate to your language later. We will produce each speaker info and speech later to upload here. So you don't need to worry. But it will take some time. Thank you for your understanding and support 🙏🙏🙏 Best wishes! Pi Network #Pinetwork #PiGVV
1:07

We will have around 2.5 hours of Chinese speech and and around half hour for different languages speakers. ( Most English). So please download your translator on your phone. I use Google translate voice translate. Or if you have a better one that will be great! If you can't join in or you can't understand, you can just listen to feel the energy. We are sorry we can't translate to English when we are in the meeting because there is too much information. We will translate to English soon after the conference. And you can translate to your language later. We will produce each speaker info and speech later to upload here. So you don't need to worry. But it will take some time. Thank you for your understanding and support 🙏🙏🙏 Best wishes! Pi Network #Pinetwork #PiGVV

Doris Yin 东方紫莲🪷

20,625 views • 3 years ago

Google released image creation and editing directly inside Gemini Live, allowing users to generate or modify images in real time while using the Gemini app. The feature works through live camera sharing, so users can show Gemini what they are looking at and ask it to create, adjust, or explain visuals on the spot.
0:22

Google released image creation and editing directly inside Gemini Live, allowing users to generate or modify images in real time while using the Gemini app. The feature works through live camera sharing, so users can show Gemini what they are looking at and ask it to create, adjust, or explain visuals on the spot.

Wes Roth

28,619 views • 2 months ago

Real-time translation that sounds like you 🚀 We've been building speech-to-speech simultaneous translation for a while. The newest piece is on-the-fly voice cloning: the model picks up your voice as you speak and carries it into the other language. Here's the alpha running live during our all-hands: you speak in Japanese, the room hears you in English, and it still sounds like you. It's early and the edges are rough, but this is the experience we've been building toward. Coming very soon. Demo video below 👇 #VoiceAI #SpeechAI #RealTimeTranslation #VoiceCloning #AI
1:29

Real-time translation that sounds like you 🚀 We've been building speech-to-speech simultaneous translation for a while. The newest piece is on-the-fly voice cloning: the model picks up your voice as you speak and carries it into the other language. Here's the alpha running live during our all-hands: you speak in Japanese, the room hears you in English, and it still sounds like you. It's early and the edges are rough, but this is the experience we've been building toward. Coming very soon. Demo video below 👇 #VoiceAI #SpeechAI #RealTimeTranslation #VoiceCloning #AI

Kotoba

66,661 views • 1 day ago

Ok I've used Codex 5.4 Extra High for something that saved me so many hours and thousands of dollars and may interest you: -> how I automatically translate my game in 9 languages 1) I did the whole game in English, with no localization in mind 2) Then everybody told me that the reach is way higher by adding local languages 3) So I had a long chat with Codex to write a great spec to build a localization interface and super simple process for afterwards (I want to keep the simplicity) 4) Then translated the game in 9 languages! 5) Every localization is challenged a second time to improve 6) We are talking 580 keys per language - it took 1h35 to find all the hardcoded text and add keys - then it took 1h15 min to do all v1 translations 7) BONUS: it translates automatically all audio with ElevenLabs (using their text to speech skill) Total: Roughly 3 hours to implement a translation system and to translate the game Can any Japanese person tell me if the translation is good? There were 2 challenges: - translating once - keeping the game translated Now it's a blessing: I still work on the game like the usual, and if I add new text, it will automatically create the keys and translate in all languages just with basic instructions in Agents.md + a pre-commit hook to ensure it's done. I hope to use the tool for a professional or community-based human review in the future! Hope it helps:)
1:04

Ok I've used Codex 5.4 Extra High for something that saved me so many hours and thousands of dollars and may interest you: -> how I automatically translate my game in 9 languages 1) I did the whole game in English, with no localization in mind 2) Then everybody told me that the reach is way higher by adding local languages 3) So I had a long chat with Codex to write a great spec to build a localization interface and super simple process for afterwards (I want to keep the simplicity) 4) Then translated the game in 9 languages! 5) Every localization is challenged a second time to improve 6) We are talking 580 keys per language - it took 1h35 to find all the hardcoded text and add keys - then it took 1h15 min to do all v1 translations 7) BONUS: it translates automatically all audio with ElevenLabs (using their text to speech skill) Total: Roughly 3 hours to implement a translation system and to translate the game Can any Japanese person tell me if the translation is good? There were 2 challenges: - translating once - keeping the game translated Now it's a blessing: I still work on the game like the usual, and if I add new text, it will automatically create the keys and translate in all languages just with basic instructions in Agents.md + a pre-commit hook to ensure it's done. I hope to use the tool for a professional or community-based human review in the future! Hope it helps:)

Nicolas Zullo

13,418 views • 4 months ago

I built an app that makes it easy to caption and translate clips while preserving the original voice. built for global communities and the creators who help them grow. a town hall can’t fit every timezone. for example, “Meet at the Clubhouse” by Bored Ape Yacht Club 🍌 or the “OG Show” by Grateful Ape🍌 + Other Games are digital social experiences I can’t attend live due to scheduling. so communities and myself run on replays, highlights, and clipped moments. creators need tools to capture these cultural moments in audio easily and it deserves to travel farther than one language. now it’s even possible to cross language barriers without losing the speaker’s voice. dubbing is powered by ElevenLabs, which I believe is leading in frontier voice and speech models. community creators and ambassadors can localize moments that matter most, making important updates easier to understand in their audience’s native language. and even without dubbing & translation, it’s great to make beautifully designed audiograms. private beta at the moment. public soon. so what do you think? does it translate well to your language? worth building out further? let me know
1:00

I built an app that makes it easy to caption and translate clips while preserving the original voice. built for global communities and the creators who help them grow. a town hall can’t fit every timezone. for example, “Meet at the Clubhouse” by Bored Ape Yacht Club 🍌 or the “OG Show” by Grateful Ape🍌 + Other Games are digital social experiences I can’t attend live due to scheduling. so communities and myself run on replays, highlights, and clipped moments. creators need tools to capture these cultural moments in audio easily and it deserves to travel farther than one language. now it’s even possible to cross language barriers without losing the speaker’s voice. dubbing is powered by ElevenLabs, which I believe is leading in frontier voice and speech models. community creators and ambassadors can localize moments that matter most, making important updates easier to understand in their audience’s native language. and even without dubbing & translation, it’s great to make beautifully designed audiograms. private beta at the moment. public soon. so what do you think? does it translate well to your language? worth building out further? let me know

NANA

12,397 views • 1 month ago

I just added real-time AI translation into Chormex using GPT-Realtime-2… and this feels absolutely surreal. It works across YouTube videos, live streams, meetings, presentations, basically anywhere audio is playing inside Chrome. You can watch translated speech in real time while simultaneously using Codex on top of the live context. “Summarize this.” “What are the key points?” “Turn this into notes.” “Explain what they mean.” “Organize the discussion.” …all while the video or meeting is still happening. It genuinely feels like browsers are evolving into real-time AI operating systems. We are getting dangerously close to a world where language barriers on the internet completely disappear.
1:29

I just added real-time AI translation into Chormex using GPT-Realtime-2… and this feels absolutely surreal. It works across YouTube videos, live streams, meetings, presentations, basically anywhere audio is playing inside Chrome. You can watch translated speech in real time while simultaneously using Codex on top of the live context. “Summarize this.” “What are the key points?” “Turn this into notes.” “Explain what they mean.” “Organize the discussion.” …all while the video or meeting is still happening. It genuinely feels like browsers are evolving into real-time AI operating systems. We are getting dangerously close to a world where language barriers on the internet completely disappear.

CHOI

191,487 views • 3 months ago

We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog Paper Can a speech AI think deeply without pausing to process? In real conversation, we don’t wait until we’ve fully worked out what we want to say—we start talking, and our thoughts catch up as the sentence unfolds. Fast speech-to-speech models achieve this, but their reasoning tends to stay shallow. Cascaded pipelines that route through a knowledgeable LLM are smarter, but the added latency breaks the flow—they fall back to "think, then speak." In our new paper, we propose a way to break this trade-off. We call it KAME (Turtle in Japanese). A speech-to-speech model handles the fast response loop and starts replying immediately. In parallel, a backend LLM runs asynchronously, generating response candidates that are continuously injected as "oracle" signals in real time. This shifts the AI paradigm from "think, then speak" to "speak while thinking." The backend LLM is completely swappable. You can plug in GPT-4.1, Claude Opus, or Gemini 2.5 Flash depending on the task without changing the frontend. In our experiments, Claude tended to score higher on reasoning, while GPT did better on humanities questions. Try the model yourself here:
0:20

We’re excited to introduce KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speech-to-Speech Conversational AI, accepted at #ICASSP2026! 🐢 Blog Paper Can a speech AI think deeply without pausing to process? In real conversation, we don’t wait until we’ve fully worked out what we want to say—we start talking, and our thoughts catch up as the sentence unfolds. Fast speech-to-speech models achieve this, but their reasoning tends to stay shallow. Cascaded pipelines that route through a knowledgeable LLM are smarter, but the added latency breaks the flow—they fall back to "think, then speak." In our new paper, we propose a way to break this trade-off. We call it KAME (Turtle in Japanese). A speech-to-speech model handles the fast response loop and starts replying immediately. In parallel, a backend LLM runs asynchronously, generating response candidates that are continuously injected as "oracle" signals in real time. This shifts the AI paradigm from "think, then speak" to "speak while thinking." The backend LLM is completely swappable. You can plug in GPT-4.1, Claude Opus, or Gemini 2.5 Flash depending on the task without changing the frontend. In our experiments, Claude tended to score higher on reasoning, while GPT did better on humanities questions. Try the model yourself here:

Sakana AI

293,975 views • 3 months 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.
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 views • 5 months ago

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!
1:05

Today, Search Live is available in English in the U.S. — no Labs opt-in required. ✨ You can now have a free-flowing, back-and-forth conversation with Search using your voice and phone camera. Live in Search combines the power of Google Lens and AI Mode to see and accurately identify objects in front of you. This allows Search to understand exactly what you are looking at and help you find the most relevant information across the web to respond to your questions in real time. Try it today by tapping Live in the Google app (iOS and Android) or Lens, and let us know what you think!

Google AI

48,572 views • 11 months ago

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!
1:25

Excited about the launch of Amazon Nova Sonic, our new speech-to-speech model that helps make AI voice applications feel remarkably natural. It's designed to understand not just what people say, but how they say it – working with tone, style, and conversation flow including pauses and interruptions. Nova Sonic delivers speech understanding and generation through a single, unified model, making it easier for builders to develop voice applications that maintain important context and nuance for customer service, AI agents, and other use cases across industries. It’s available in Amazon Bedrock now. Look forward to seeing what teams build with Nova Sonic!

Andy Jassy

155,882 views • 1 year ago

🚨UPDATE: I never thought that Typing could get Typeless! Meet Typeless 1.0.2 for Mac that has made your voice so powerful. Dictate, Translate & Ask anything in any language or accent and #Typeless 1.0.2 will type it for you 10x faster with errors fixed. 1/ Dictation: With Typeless dictation, you'll get the smartest voice keyboard that understands your intent, helps organize thoughts, and turns your natural speech into clear, structured, perfect writing in every application. Press "Fn" Key to start and stop dictation. Or hold to say something short. 2/ Translation: With Typeless translation, you can talk in your own first language, and Typeless will translate it into any target language—empowering you to write in every foreign language just like a native speaker. "Fn" + "Space" Keys to Start Translation and "Fn" Key to stop translation. 3/ Ask Anything: With Typeless Ask Anything, you can use your voice to make edits to any selected text and simply say how you want to change it, get quick answers, and do quick actions. Press "Fn" + "Space" Keys to start ask anything and "Fn" stop asking anything.
8:26

🚨UPDATE: I never thought that Typing could get Typeless! Meet Typeless 1.0.2 for Mac that has made your voice so powerful. Dictate, Translate & Ask anything in any language or accent and #Typeless 1.0.2 will type it for you 10x faster with errors fixed. 1/ Dictation: With Typeless dictation, you'll get the smartest voice keyboard that understands your intent, helps organize thoughts, and turns your natural speech into clear, structured, perfect writing in every application. Press "Fn" Key to start and stop dictation. Or hold to say something short. 2/ Translation: With Typeless translation, you can talk in your own first language, and Typeless will translate it into any target language—empowering you to write in every foreign language just like a native speaker. "Fn" + "Space" Keys to Start Translation and "Fn" Key to stop translation. 3/ Ask Anything: With Typeless Ask Anything, you can use your voice to make edits to any selected text and simply say how you want to change it, get quick answers, and do quick actions. Press "Fn" + "Space" Keys to start ask anything and "Fn" stop asking anything.

Wesley

173,808 views • 6 months ago

Viggle’s Mic 2.0 is here! With our upgraded model, take precise control over how a character talks and moves, in one shot. Turn images into videos simply with an audio or text prompt for speech. Or take it further—add a motion source to drive the character’s movements—action and voice, perfectly aligned. Try it free on our web, or on our iOS/Android apps.👇
0:33

Viggle’s Mic 2.0 is here! With our upgraded model, take precise control over how a character talks and moves, in one shot. Turn images into videos simply with an audio or text prompt for speech. Or take it further—add a motion source to drive the character’s movements—action and voice, perfectly aligned. Try it free on our web, or on our iOS/Android apps.👇

ViggleAI

36,121 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 🧵↓
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 views • 7 months ago