Загрузка видео...

Не удалось загрузить видео

На главную

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%. 📉

OpenAIDevs's profile picture

OpenAI Developers

396,261 subscribers

243,432 просмотров • 1 год назад •via X (Twitter)

Наука и технологииОбразованиеНовости и политика
LIVE

Anya Rossi• Live Now

Private livecam show

Комментарии: 10

Фото профиля Vaibhav (VB) Srivastav
Vaibhav (VB) Srivastav1 год назад

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

Фото профиля Degen Wave 🌊
Degen Wave 🌊1 год назад

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

Фото профиля Mckay Wrigley
Mckay Wrigley1 год назад

This one is super appreciated!

Фото профиля Alex Volkov (Thursd/AI)
Alex Volkov (Thursd/AI)1 год назад

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? 🙏

Фото профиля Daniel Nguyen ⚡
Daniel Nguyen ⚡1 год назад

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

Фото профиля •
•1 год назад

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

Фото профиля Haider.
Haider.1 год назад

ok, but what's so funny?

Фото профиля Everett World
Everett World1 год назад

Nice, but Sol is still the best voice!

Фото профиля Jan
Jan1 год назад

we need an updated text to speech api : (

Фото профиля Kol Tregaskes
Kol Tregaskes1 год назад

Liking the new voices.

Похожие видео

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.
0:39

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

155,500 просмотров • 1 год назад

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.
0:36

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 просмотров • 1 год назад

🎥 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)
1:30

🎥 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

192,261 просмотров • 11 месяцев назад

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!
0:33

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

805,885 просмотров • 5 месяцев назад

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:
0:27

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 просмотров • 9 месяцев назад

🎵 ✨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.
3:03

🎵 ✨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

90,418 просмотров • 1 год назад

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]
0:31

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

8,188,968 просмотров • 1 год назад

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

203,435 просмотров • 5 месяцев назад

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! 🚀
0:54

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 просмотров • 1 год назад

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 ⭐️
4:29

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

164,026 просмотров • 7 месяцев назад

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 🤗
1:21

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

299,066 просмотров • 1 год назад

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.
1:41

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

55,915 просмотров • 3 лет назад

NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone Most unified audio models pay a text tax. Add audio output, and reasoning benchmarks drop — even when the only new output is speech. NVIDIA just released one that doesn't. Audex (Nemotron-Labs-Audex-30B-A3B) is a 30B MoE with 3B active parameters, built on the text-only Nemotron-Cascade-2-30B-A3B backbone. Audio inputs are projected into the text embedding space. Text tokens and quantized audio tokens are then generated the same way, inside one MoE decoder — no thinker–talker split, no stacked cascade. Here's what's actually interesting: → One model, audio in and out: understanding, ASR, translation, TTS, text-to-audio, speech-to-speech → Text holds vs its own backbone: IMO AnswerBench 81.1 vs 79.3, MMLU-Redux 86.4 vs 86.3 → Beats text-only Qwen3.5-35B-A3B on several tasks: LiveCodeBench v6 85.3 vs 74.6, IFBench 77.8 vs 70.2 → The usual tax, for contrast: Qwen3-Omni-30B-A3B-Thinking drops to 60.4 on HMMT vs 71.4 for its text backbone → 6.82 WER on OpenASR, ahead of Step-Audio-R1.1-33B (7.91) and Qwen3-Omni-Thinking (8.00) → Two codecs: X-Codec2 for speech (50 tok/s, FSQ, 65,536 codebook), X-Codec for general audio (200 tok/s, 4 flattened RVQ layers) — the only strong open model generating general audio beyond speech Full analysis: Paper: Model weights: NVIDIA AI NVIDIA Wei Ping
0:27

NVIDIA Releases Audex (Nemotron-Labs-Audex-30B-A3B): A Unified Audio-Text LLM That Preserves the Text Intelligence of Its Backbone Most unified audio models pay a text tax. Add audio output, and reasoning benchmarks drop — even when the only new output is speech. NVIDIA just released one that doesn't. Audex (Nemotron-Labs-Audex-30B-A3B) is a 30B MoE with 3B active parameters, built on the text-only Nemotron-Cascade-2-30B-A3B backbone. Audio inputs are projected into the text embedding space. Text tokens and quantized audio tokens are then generated the same way, inside one MoE decoder — no thinker–talker split, no stacked cascade. Here's what's actually interesting: → One model, audio in and out: understanding, ASR, translation, TTS, text-to-audio, speech-to-speech → Text holds vs its own backbone: IMO AnswerBench 81.1 vs 79.3, MMLU-Redux 86.4 vs 86.3 → Beats text-only Qwen3.5-35B-A3B on several tasks: LiveCodeBench v6 85.3 vs 74.6, IFBench 77.8 vs 70.2 → The usual tax, for contrast: Qwen3-Omni-30B-A3B-Thinking drops to 60.4 on HMMT vs 71.4 for its text backbone → 6.82 WER on OpenASR, ahead of Step-Audio-R1.1-33B (7.91) and Qwen3-Omni-Thinking (8.00) → Two codecs: X-Codec2 for speech (50 tok/s, FSQ, 65,536 codebook), X-Codec for general audio (200 tok/s, 4 flattened RVQ layers) — the only strong open model generating general audio beyond speech Full analysis: Paper: Model weights: NVIDIA AI NVIDIA Wei Ping

Marktechpost AI

28,301 просмотров • 2 месяцев назад

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
1:59

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

396,694 просмотров • 6 месяцев назад

Our inspect services are now integrated with the CS2 Trader extension! Made by fellow trader Gergely Szabo This means ST and Agent codes are now supported and you can connect to servers with ease 🥳 More to come 🤫
0:23

Our inspect services are now integrated with the CS2 Trader extension! Made by fellow trader Gergely Szabo This means ST and Agent codes are now supported and you can connect to servers with ease 🥳 More to come 🤫

Epidemic

10,346 просмотров • 2 лет назад

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. 👉 👉
2:24

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

41,235 просмотров • 10 месяцев назад

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."
3:34

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 просмотров • 1 год назад