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.

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

330,153 subscribers

243,205 views • 1 year ago •via X (Twitter)

Science & Technology Education News & Politics

Anya Rossi• Live Now

Private livecam show

10 Comments

Vaibhav (VB) Srivastav1 year ago

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

Degen Wave 🌊1 year ago

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

Mckay Wrigley1 year ago

This one is super appreciated!

Alex Volkov (Thursd/AI)1 year ago

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 ⚡1 year ago

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

•1 year ago

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

Haider.1 year ago

ok, but what's so funny?

Everett World1 year ago

Nice, but Sol is still the best voice!

Jan1 year ago

we need an updated text to speech api : (

Kol Tregaskes1 year ago

Liking the new voices.

Related Videos

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

155,360 views • 1 year ago

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

351,674 views • 1 year ago

🎥 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

192,167 views • 8 months ago

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

799,839 views • 2 months ago

PSA: Our intern Dylan Mitic (the people's prince) screwed up again and reduced prices for GPT OSS models on Groq Inc, but we're rolling with it. 20-40% price reductions + 50% off cached tokens with prompt caching for 20B (120B coming soon). Fast and even more affordable. 🫡

PSA: Our intern Dylan Mitic (the people's prince) screwed up again and reduced prices for GPT OSS models on Groq Inc, but we're rolling with it. 20-40% price reductions + 50% off cached tokens with prompt caching for 20B (120B coming soon). Fast and even more affordable. 🫡

Hatice Ozen

84,974 views • 8 months ago

🚨Today we’re rolling out Prompt Caching on GroqCloud. Keep hot prompts in memory, cut cached token costs by 50% and slash latency. Faster response, smarter inference. Learn more 👇

🚨Today we’re rolling out Prompt Caching on GroqCloud. Keep hot prompts in memory, cut cached token costs by 50% and slash latency. Faster response, smarter inference. Learn more 👇

Groq Inc

20,383 views • 9 months ago

Here are the best practices for using Eleven v3 (alpha) - the most expressive Text to Speech model.

Here are the best practices for using Eleven v3 (alpha) - the most expressive Text to Speech model.

ElevenLabs

43,692 views • 1 year ago

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 views • 6 months ago

🎵 ✨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 views • 1 year ago

Here are the experiences developers are building with the Realtime API:

Here are the experiences developers are building with the Realtime API:

OpenAI Developers

34,306 views • 6 days ago

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

8,188,608 views • 9 months ago

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡

Mini-Omni 2 understands image, audio and text inputs all via end-to-end voice conversations with users 🔥 > Understands and processes images, speech, and text > Generates real-time speech responses > Supports interruptions during speech Technical Overview: > Concatenates image, audio, and text features for input. > Uses text-guided delayed parallel output for real-time speech > Involves encoder adaptation, modal alignment, and multimodal fine-tuning Best part: MIT licensed ⚡

Vaibhav (VB) Srivastav

45,409 views • 1 year ago

POV: You gave every accent a World Cup mic 🌍 Pollo AI Audio is now live! Text-to-Speech + expressive voices. Try it:

POV: You gave every accent a World Cup mic 🌍 Pollo AI Audio is now live! Text-to-Speech + expressive voices. Try it:

Pollo AI

1,369,224 views • 18 days ago

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

🔊Introducing Voxtral TTS: our new frontier open-weight model for natural, expressive, and ultra-fast text-to-speech 🎭Realistic, emotionally expressive speech. 🌍Supports 9 languages and accurately captures diverse dialects. ⚡Very low latency for time-to-first-audio. 🔄Easily adaptable to new voices

Mistral AI

895,250 views • 2 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 ↓

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

201,925 views • 2 months ago

That’s it. That’s the tweet. The Realtime API now supports WebRTC—you can add Realtime capabilities with just a handful of lines of code. We’ve also cut prices by 60%, added GPT-4o mini (10x cheaper than previous prices), improved voice quality, and made inputs more reliable.

That’s it. That’s the tweet. The Realtime API now supports WebRTC—you can add Realtime capabilities with just a handful of lines of code. We’ve also cut prices by 60%, added GPT-4o mini (10x cheaper than previous prices), improved voice quality, and made inputs more reliable.

OpenAI Developers

523,470 views • 1 year ago

Some examples: - Text to Speech: Read aloud content or create audiobooks. - Speech to Text: Transcribe audio and video into text. - Voice Designer: Create custom AI voices. - Conversational AI: Build dynamic voice agents and make outbound calls.

Some examples: - Text to Speech: Read aloud content or create audiobooks. - Speech to Text: Transcribe audio and video into text. - Voice Designer: Create custom AI voices. - Conversational AI: Build dynamic voice agents and make outbound calls.

ElevenLabs

19,318 views • 1 year ago

PSA: Prompt caching is now live for moonshotai/kimi-k2-instruct on Groq Inc: → 50% discount for cached tokens → Lower latency → Automatic prefix matching Excited to roll this out starting with Kimi K2 and even more excited for inexpensive, fast vibe coding for all. ⚡️

PSA: Prompt caching is now live for moonshotai/kimi-k2-instruct on Groq Inc: → 50% discount for cached tokens → Lower latency → Automatic prefix matching Excited to roll this out starting with Kimi K2 and even more excited for inexpensive, fast vibe coding for all. ⚡️

Hatice Ozen

67,965 views • 9 months ago

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

22,962 views • 1 year ago

The Realtime API is officially out of beta and ready for your production voice agents! We’re also introducing gpt-realtime—our most advanced speech-to-speech model yet—plus new voices and API capabilities: 🔌 Remote MCPs 🖼️ Image input 📞 SIP phone calling ♻️ Reusable prompts

The Realtime API is officially out of beta and ready for your production voice agents! We’re also introducing gpt-realtime—our most advanced speech-to-speech model yet—plus new voices and API capabilities: 🔌 Remote MCPs 🖼️ Image input 📞 SIP phone calling ♻️ Reusable prompts

OpenAI Developers

561,626 views • 9 months ago