正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Two Realtime API updates: - You can now build speech-to-speech experiences with five new voices—which are much more expressive and steerable. 🤣🤫🤪 - We're lowering the price by using prompt caching. Cached text inputs are discounted 50% and cached audio inputs are discounted 80%. 📉

OpenAI Developers

385,353 subscribers

243,333 次观看 • 1 年前 •via X (Twitter)

科学技术教育新闻政治

Anya Rossi• Live Now

Private livecam show

10 条评论

Vaibhav (VB) Srivastav 的头像

Vaibhav (VB) Srivastav1 年前

Congratulations - our cascaded approach has had that for quite a long while 🤗

Degen Wave 🌊 的头像

Degen Wave 🌊1 年前

Can we get a voice that is at least close to being as good as Sky was plz?

Mckay Wrigley 的头像

Mckay Wrigley1 年前

This one is super appreciated!

Alex Volkov (Thursd/AI) 的头像

Alex Volkov (Thursd/AI)1 年前

Can we get some clarification / confirmation of the following? - are output tokens are turned into input tokens on next turn? - Is the caching automatic or do we need to do anything? - can we get an example calculation of a 3 turn conversation and transparent pricing? 🙏

Daniel Nguyen ⚡ 的头像

Daniel Nguyen ⚡1 年前

Thank you. Can you add sample audio so we can add voice preview in our app? Similar to mp3 files on this page

• 的头像

•1 年前

“Sorry, that’s against my guidelines” is what needs to be fixed most

Haider. 的头像

Haider.1 年前

ok, but what's so funny?

Everett World 的头像

Everett World1 年前

Nice, but Sol is still the best voice!

Jan 的头像

Jan1 年前

we need an updated text to speech api : (

Kol Tregaskes 的头像

Kol Tregaskes1 年前

Liking the new voices.

相关视频

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

Google

155,449 次观看 • 1 年前

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

Today we released Meta Spirit LM — our first open source multimodal language model that freely mixes text and speech. Many existing AI voice experiences today use ASR to techniques to process speech before synthesizing with an LLM to generate text — but these approaches compromise the expressive aspects of speech. Using phonetic, pitch and tone tokens, Spirit LM models can overcome these limitations for both inputs and outputs to generate more natural sounding speech while also learning new tasks across ASR, TTS and speech classification. We hope that sharing this work will enable the research community to further new approaches for text and speech integration.

AI at Meta

351,764 次观看 • 1 年前

🎥 Sora 2 and Sora 2 Pro are now in the API. And new image and speech-to-speech models that are cheaper than their full-sized counterparts, but with similar quality: 📸 gpt-image-1-mini (80% cheaper) 🗣️ gpt-realtime-mini (70% cheaper)

🎥 Sora 2 and Sora 2 Pro are now in the API. And new image and speech-to-speech models that are cheaper than their full-sized counterparts, but with similar quality: 📸 gpt-image-1-mini (80% cheaper) 🗣️ gpt-realtime-mini (70% cheaper)

OpenAI Developers

192,214 次观看 • 10 个月前

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Introducing Gemini 3.1 Flash TTS 🗣️, our latest text to speech model with scene direction, speaker level specificity, audio tags, more natural + expressive voices, and support for 70 different languages. Available via our new audio playground in AI Studio and in the Gemini API!

Logan Kilpatrick

803,494 次观看 • 3 个月前

people always ask me how they can create long, consistent AI videos with audio. well creatify aurora solves a big part of that and there are some new models coming soon too for more action + audio. I created his voice with dia tts which i think great at capturing emotional speeches. then I cloned his voice using minimax voice clone and use it on minimax tts 2.6. here is the my full conversation with claude for images and text to speech inputs:

people always ask me how they can create long, consistent AI videos with audio. well creatify aurora solves a big part of that and there are some new models coming soon too for more action + audio. I created his voice with dia tts which i think great at capturing emotional speeches. then I cloned his voice using minimax voice clone and use it on minimax tts 2.6. here is the my full conversation with claude for images and text to speech inputs:

gokaygokay

38,341 次观看 • 7 个月前

🎵 ✨The world’s most flexible sound machine? With text and audio inputs, this new #generativeAI model, named Fugatto, can create any combination of music, voices, and sounds.🎹 Read more in our blog by richardkerris ➡️ #NVIDIAResearch Note: Some music, sounds, and the voice of NVIDIA CEO Jensen Huang used in this video are AI generated.

🎵 ✨The world’s most flexible sound machine? With text and audio inputs, this new #generativeAI model, named Fugatto, can create any combination of music, voices, and sounds.🎹 Read more in our blog by richardkerris ➡️ #NVIDIAResearch Note: Some music, sounds, and the voice of NVIDIA CEO Jensen Huang used in this video are AI generated.

NVIDIA AI Developer

90,328 次观看 • 1 年前

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

ElevenLabs

8,188,671 次观看 • 11 个月前

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 ↓

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

202,949 次观看 • 3 个月前

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

I made a few updates to the MLX port of F5 TTS over the holiday: - Longform generation is now supported, and text will be split automatically on sentence boundaries for natural-sounding speech. - You can now pipe in text from another process (e.g. a language model) and listen to the speech as each segment is generated. - I implemented RK4 sampling for the ODE, which achieves much better quality with fewer steps — it's now possible to generate speech at 1.6x realtime on my M3 Max. See the video of an example of generating speech in realtime from a language model entirely on-device! 🚀

Lucas Newman

22,998 次观看 • 1 年前

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️

Day 1 of 3 days of MLX: Introducing MLX-Audio-Swift SDK 🚀 A modular Swift SDK for voice agents and tasks on Apple Silicon built by Lucas Newman and yours truly. iOS, macOS, and visionOS developers can now build native apps with real-time, on-device audio intelligence: 🗣️ Text-to-Speech (TTS) 👂 Speech-to-Text (STT) 🔄 Speech-to-Speech (STS) 🎙️ Voice Activity Detection (VAD) and more. Only import the capabilities you need, nothing extra. Get started today and leave us a star ⭐️

Prince Canuma

163,744 次观看 • 5 个月前

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

Vaibhav (VB) Srivastav

298,953 次观看 • 1 年前

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Speak with ChatGPT: You can now use voice to engage in a back-and-forth conversation with your assistant. The hyper-realistic text-to-speech model allows you to choose from five different voices. On mobile, opt-in to voice in Settings → New Features on the mobile app.

Rowan Cheung

55,777 次观看 • 2 年前

Finally here! Dreamina Seedance 2.0 and Seedream 5.0 Lite are Now Available on Dreamina AI We're excited to introduce our latest models, which are built for deeper control and broader creative possibilities. What Makes Dreamina Seedance 2.0 Exceptional? → Multimodal video model → Reference with image, video, and text inputs → Ultimate consistency across multiple scenes → More expressive, more controllable Create images with Seedream 5.0 Lite → Real-time world knowledge → Follows your prompts, delivers precise results → Upgraded visual expression We are gradually rolling out Dreamina Seedance 2.0 and Seedream 5.0 Lite to our community over the coming days. Hang tight if you don't see it yet and check back soon. Try it now: #DreaminaSeedance2 #DreaminaAI #Seedream5Lite #Seedance2

Finally here! Dreamina Seedance 2.0 and Seedream 5.0 Lite are Now Available on Dreamina AI We're excited to introduce our latest models, which are built for deeper control and broader creative possibilities. What Makes Dreamina Seedance 2.0 Exceptional? → Multimodal video model → Reference with image, video, and text inputs → Ultimate consistency across multiple scenes → More expressive, more controllable Create images with Seedream 5.0 Lite → Real-time world knowledge → Follows your prompts, delivers precise results → Upgraded visual expression We are gradually rolling out Dreamina Seedance 2.0 and Seedream 5.0 Lite to our community over the coming days. Hang tight if you don't see it yet and check back soon. Try it now: #DreaminaSeedance2 #DreaminaAI #Seedream5Lite #Seedance2

Dreamina AI

395,609 次观看 • 4 个月前

At a time when our values, our health care and even our free speech are on the line, thank you for choosing to lift your voices with purpose, with peace and with precision by phone banking voters to Save Our Health Care and pass Prop 50! -NP

At a time when our values, our health care and even our free speech are on the line, thank you for choosing to lift your voices with purpose, with peace and with precision by phone banking voters to Save Our Health Care and pass Prop 50! -NP

Nancy Pelosi

88,139 次观看 • 10 个月前

Justice Thomas’s words on free speech three years ago are needed now more than ever: “To me, the epicenter of free speech, when I was at the university, that’s where you learned how to engage with people who disagreed with you, that’s where you learned how to deal with ideas and address ideas with which you were not familiar previously or with which you disagreed...This is where you learned how to deal with views that are different.”

Justice Thomas’s words on free speech three years ago are needed now more than ever: “To me, the epicenter of free speech, when I was at the university, that’s where you learned how to engage with people who disagreed with you, that’s where you learned how to deal with ideas and address ideas with which you were not familiar previously or with which you disagreed...This is where you learned how to deal with views that are different.”

Carrie Severino

25,794 次观看 • 10 个月前

World Labs and VIVE Mars are making it easier to turn ideas into shoot-ready 3D scenes, fast. World Labs new AI world-builder lets you create detailed virtual environments from a simple text or image prompt, then composite them live. Once the scene is ready, you can step straight into production using VIVE Mars CamTrack. Sign up at a discounted rate to start building worlds, and see how the full workflow comes together with VIVE Mars CamTrack and Marble. 👉 👉

World Labs and VIVE Mars are making it easier to turn ideas into shoot-ready 3D scenes, fast. World Labs new AI world-builder lets you create detailed virtual environments from a simple text or image prompt, then composite them live. Once the scene is ready, you can step straight into production using VIVE Mars CamTrack. Sign up at a discounted rate to start building worlds, and see how the full workflow comes together with VIVE Mars CamTrack and Marble. 👉 👉

HTC VIVE

40,988 次观看 • 8 个月前

Jeff Bezos: “Focus on the controllable inputs to your business instead of the outputs” Jeff gives the example of companies trying to drive up their stock price by actually going out and trying to sell their stock: “[A higher stock price] is the final output…. That’s not going to be sustainable. It’s a silly approach.” Jeff recommends working backwards from a higher stock price to its controllable inputs instead: “What are the inputs to a higher stock price? Okay, well, free cash flow and return on invested capital are inputs to a higher stock price. Let’s keep working backwards. What are the inputs to free cash flow? And you keep working backwards until you get to something that’s controllable.” He points out that a controllable input to free cash flow would be something like a lower cost structure: “If we can improve our picking efficiency in our fulfillment centers and reduce defects - reducing defects at the root is one of the best ways to lower cost structure - that starts to be a job you would accept. If you’re a reasonable person, you would say, I have no idea how to drive up the stock price - I can’t manage that directly. It’s not a controllable input. But I can make your picking algorithms more efficient, and that will reduce cost structure. And then you follow that chain all along the way. That’s what you do in all of these businesses.” Video source: Business Insider (2014)

Jeff Bezos: “Focus on the controllable inputs to your business instead of the outputs” Jeff gives the example of companies trying to drive up their stock price by actually going out and trying to sell their stock: “[A higher stock price] is the final output…. That’s not going to be sustainable. It’s a silly approach.” Jeff recommends working backwards from a higher stock price to its controllable inputs instead: “What are the inputs to a higher stock price? Okay, well, free cash flow and return on invested capital are inputs to a higher stock price. Let’s keep working backwards. What are the inputs to free cash flow? And you keep working backwards until you get to something that’s controllable.” He points out that a controllable input to free cash flow would be something like a lower cost structure: “If we can improve our picking efficiency in our fulfillment centers and reduce defects - reducing defects at the root is one of the best ways to lower cost structure - that starts to be a job you would accept. If you’re a reasonable person, you would say, I have no idea how to drive up the stock price - I can’t manage that directly. It’s not a controllable input. But I can make your picking algorithms more efficient, and that will reduce cost structure. And then you follow that chain all along the way. That’s what you do in all of these businesses.” Video source: Business Insider (2014)

Startup Archive

18,881 次观看 • 1 年前

We asked Dylan Field about organizational design in the age of AI, the importance of design. "As the inputs to software change, as more people are creating software, design becomes the differentiator." "Two decades ago, design was lipstick on a pig." "Design now is how you win or lose. We're going to start seeing so many more designer CEOs and design-oriented folks who are leading and shaping the future of software and companies." "Incredible designers are more in demand than ever. Good luck recruiting them because they have 50 other offers and infinite optionality."

We asked Dylan Field about organizational design in the age of AI, the importance of design. "As the inputs to software change, as more people are creating software, design becomes the differentiator." "Two decades ago, design was lipstick on a pig." "Design now is how you win or lose. We're going to start seeing so many more designer CEOs and design-oriented folks who are leading and shaping the future of software and companies." "Incredible designers are more in demand than ever. Good luck recruiting them because they have 50 other offers and infinite optionality."

TBPN

27,940 次观看 • 1 年前

We asked Gajesh about AVSs coming out that are top of the line. "Opacity’s zkTLS is an amazing product." "You can prove any private data right now and it unlocks so much capabilities." "We also have other services like WITNESS who have proof of location services." "With EigenCompute and EigenVerify coming in, you can build, we're making crypto more expressive." "Here with you can just write code, upload it to our platform."

We asked Gajesh about AVSs coming out that are top of the line. "Opacity’s zkTLS is an amazing product." "You can prove any private data right now and it unlocks so much capabilities." "We also have other services like WITNESS who have proof of location services." "With EigenCompute and EigenVerify coming in, you can build, we're making crypto more expressive." "Here with you can just write code, upload it to our platform."

The Rollup

11,331 次观看 • 1 年前

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

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 次观看 • 3 个月前