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.

Today, we're introducing PlayDialog beta. It's a SOTA voice model built for fluid, emotive, human-like conversation. PlayDialog lets you create engaging dialog and speaker narrative programmatically -- and from documents, URLs, or text. Nothing else sounds as human.

PlayAI

15,172 subscribers

40,871 views • 1 year ago •via X (Twitter)

Gaming Science & Technology

Anya Rossi• Live Now

Private livecam show

10 Comments

PlayAI (formerly PlayHT)1 year ago

What makes PlayDialog special? It takes the full history of previous prompts and responses as input to generate a response that’s emotionally coherent and fluid.

PlayAI (formerly PlayHT)1 year ago

And stories sound better than ever. The narrators in our synthetic podcasts sound like they’re feeding off each other -- just like in real life.

PlayAI (formerly PlayHT)1 year ago

But... hearing is believing. So we built PlayNote, too. Just drop in any file or website link, and get beautifully narrated podcasts, briefings, stories, and more.

PlayAI (formerly PlayHT)1 year ago

Within minutes you can generate fluid, emotional and accurate audio content using a selection of voices powered by PlayDialog And the best part? The whole thing is accessible via API:

PlayAI (formerly PlayHT)1 year ago

We're excited to see what you build. Read the full announcement here:

Brent Lynch1 year ago

My 5 minute + Hedra Labs & PlayAI experiment I just ran to have someone with multiple personalities discuss Play Dialog @play_ht with themselves, one personality a little more grounded than the other. Took only about a minute to generate 5 minutes of dialog audio. Video took a little longer but 5+ minutes of AI Video and dialog generated in 30 minutes total! Look forward to others experiments! @RyanMorrisonJer @TheoMediaAI @el_cine @thedorbrothers @hedra_labs @dustinhollywood @Diesol @Uncanny_Harry

Brent Lynch1 year ago

Just as an experiement I threw in a two character sample (generated in less than 30 seconds) into a single character Hedra @hedra_labs without any tweaks. Really super impressive @RyanMorrisonJer @TheoMediaAI @EHuanglu

Silvio S.1 year ago

@blovereviews considering your podcast, this might be nice

William Lamkin1 year ago

Looks and sounds impressive. Nice work!

Ahmet Koç1 year ago

when multilanguage (turkish) support for agents?

Related Videos

Today, we're introducing PlayHT2.0 - our new Conversational Text-to-Voice AI Model that's trained and built to generate humanlike conversations across languages with <1s latency. Sign up for beta access -

Today, we're introducing PlayHT2.0 - our new Conversational Text-to-Voice AI Model that's trained and built to generate humanlike conversations across languages with <1s latency. Sign up for beta access -

PlayAI

52,378 views • 2 years ago

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

Introducing — a new conversational Voice AI platform and API for creating human-like voice agents and voice interfaces. Powered by our new Large Dialogue Model (LDM), Play LDM 1.0 makes the speech generation contextual; handles turn-taking, interruption, voice energy and emotion modulation for a natural, fluid, human conversations in real-time.

PlayAI

105,616 views • 2 years ago

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,142,415 views • 1 month ago

Introducing Wan 2.5 🚀 Create immersive AI videos with fluid motion, built-in audio and voice. Supporting text-to-video and start images Available now for all users

Introducing Wan 2.5 🚀 Create immersive AI videos with fluid motion, built-in audio and voice. Supporting text-to-video and start images Available now for all users

Magnific

170,229 views • 9 months ago

Introducing Voice Agent Builder: a no-code platform to create human-like voice agents with Grok Voice. Available today at $0.05 / min.

Introducing Voice Agent Builder: a no-code platform to create human-like voice agents with Grok Voice. Available today at $0.05 / min.

SpaceXAI

33,035,454 views • 10 days ago

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Inworld AI

324,990 views • 2 months ago

Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation.

Introducing Atlas 1. Willow's new frontier speech-to-text model. It outperforms ElevenLabs, Deepgram, OpenAI, and more by a wide margin. Built on the first scalable, human-powered transcription infrastructure ever built for real-time dictation.

Willow

835,043 views • 3 months ago

Imagine a world where your voice is the universal interface. No screens, no buttons, just seamless, human-like conversations. This is the future we're creating at PlayAI. Today, we are announcing our latest foundational voice model, Play Dialog, a multi-turn conversational voice model trained to converse like humans. And a $21m seed funding to fuel our research and product development efforts. Join us in building the future of conversational voice ai.

Imagine a world where your voice is the universal interface. No screens, no buttons, just seamless, human-like conversations. This is the future we're creating at PlayAI. Today, we are announcing our latest foundational voice model, Play Dialog, a multi-turn conversational voice model trained to converse like humans. And a $21m seed funding to fuel our research and product development efforts. Join us in building the future of conversational voice ai.

PlayAI

46,742 views • 1 year ago

Play AI by vibx (YC W23) is a new platform for creating human-like voice agents. It makes speech generation contextual and handles turn-taking, interruption, voice energy, and emotion modulation for natural, fluid, human conversations in real-time.

Play AI by vibx (YC W23) is a new platform for creating human-like voice agents. It makes speech generation contextual and handles turn-taking, interruption, voice energy, and emotion modulation for natural, fluid, human conversations in real-time.

Y Combinator

21,285 views • 2 years ago

Today, we're introducing Ideogram Tile. Create seamless repeating patterns from a single text prompt. Make wallpapers, endless textures, immersive landscapes, and more.

Today, we're introducing Ideogram Tile. Create seamless repeating patterns from a single text prompt. Make wallpapers, endless textures, immersive landscapes, and more.

Ideogram

54,627 views • 2 years ago

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):

Introducing GPT-4o, our new model which can reason across text, audio, and video in real time. It's extremely versatile, fun to play with, and is a step towards a much more natural form of human-computer interaction (and even human-computer-computer interaction):

Greg Brockman

4,360,048 views • 2 years ago

Today, we’re introducing the next AI interface for creation: a person. Pika Agents are the creative partner you birth. They have a voice, face, and personality that you create. And they enable an entirely new way to make, refine, and ship anything—simply by having a human conversation. RIP prompt box. It’s time to meet your maker.

Today, we’re introducing the next AI interface for creation: a person. Pika Agents are the creative partner you birth. They have a voice, face, and personality that you create. And they enable an entirely new way to make, refine, and ship anything—simply by having a human conversation. RIP prompt box. It’s time to meet your maker.

Pika

3,541,311 views • 2 months ago

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.

🚨NEW: CHATGPT LIVE VOICE MODEL NOW DELIVERS REAL-TIME CONVERSATIONAL TRANSLATION Built on a full-duplex architecture, GPT-Live is a new generation of voice models that can listen and speak simultaneously, enabling more natural human-AI interactions. The breakthrough unlocks fluid back-and-forth conversations, real-time translation, and a far more human sense of timing and context.

Coin Bureau

29,085 views • 2 days ago

The Bowed instrument that sounds like a human voice.

The Bowed instrument that sounds like a human voice.

Brian Roemmele

22,195 views • 2 months ago

Miso One is an open-source voice model built for real-time conversations, responding in about 110 milliseconds while also cloning voices from short audio samples. Its speed makes Al voice chats feel smoother, faster, and much closer to natural human conversation

Miso One is an open-source voice model built for real-time conversations, responding in about 110 milliseconds while also cloning voices from short audio samples. Its speed makes Al voice chats feel smoother, faster, and much closer to natural human conversation

Hugging Models

15,754 views • 1 month ago

Today, we’re proud to unveil a pioneering partnership with @Groq. Our Dialog voice model now runs on GroqCloud. This isn't just an upgrade; this is a leap forward that redefines what voice technology can be—fast, powerful, and beautifully human.

Today, we’re proud to unveil a pioneering partnership with @Groq. Our Dialog voice model now runs on GroqCloud. This isn't just an upgrade; this is a leap forward that redefines what voice technology can be—fast, powerful, and beautifully human.

PlayAI

155,989 views • 1 year ago

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

If you try nothing else today, give the demo at a go - it lets you stream video and audio directly to Gemini 2.0 Flash and get audio back, so you can have a real-time audio conversation about what you can see with the model Feels like science fiction!

Simon Willison

208,965 views • 1 year ago

Introducing Motionscribe 🪄 Create great looking promo videos from text. Built for macOS.

Introducing Motionscribe 🪄 Create great looking promo videos from text. Built for macOS.

Hakim El Hattab

109,216 views • 3 years ago