Sensitive content

This media may contain sensitive content.

Загрузка видео...

Не удалось загрузить видео

Возникла проблема при загрузке этого видео. Это может быть связано с временными проблемами сети или видео может быть недоступно.

На главную

Sampl:e: - Listen with 🎧 ON: #Pornosexual Drone - my most complex audio layering with IRL voice #hypno and subliminal #goonaudio overlayed deliciously nasty Porn. Can you handle it? #pornaddict #goonharder #pornpiggy #goonencouragement #GoonCap #porncaps #PornIsLife #hypnoporn

PornRealityDarkSide

12,865 subscribers

108,443 просмотров • 2 лет назад •via X (Twitter)

NSFW #Pornosexual #hypno #goonaudio #pornaddict #goonharder #pornpiggy #goonencouragement #GoonCap #porncaps #PornIsLife #hypnoporn

Anya Rossi• Live Now

Private livecam show

Комментарии: 0

Нет доступных комментариев

Здесь появятся комментарии из оригинального поста

Похожие видео

I have done my best to transcribe the sacred audio from the pilot episode. You can hear it much better with headphones on, fyi. Most of the credit goes to 🦉Humble📚 and kit 🥞 for figuring out most of it tbh. I spent an hour of my life on this.

I have done my best to transcribe the sacred audio from the pilot episode. You can hear it much better with headphones on, fyi. Most of the credit goes to 🦉Humble📚 and kit 🥞 for figuring out most of it tbh. I spent an hour of my life on this.

🌈Kayla (Kighla)

185,412 просмотров • 1 год назад

DANCE THE NIGHT written for Barbie Movie OUT NOW EVERYWHERE!!! Watch the full video on youtube and you can listen / stream the song on all streaming platforms 🎧I wrote this song with my friends Mark Ronson Andrew Wyatt #CarolineAilin and we hope you LOVE IT! Barbie out in cinema’s July 21st!!!! 💕🪩

DANCE THE NIGHT written for Barbie Movie OUT NOW EVERYWHERE!!! Watch the full video on youtube and you can listen / stream the song on all streaming platforms 🎧I wrote this song with my friends Mark Ronson Andrew Wyatt #CarolineAilin and we hope you LOVE IT! Barbie out in cinema’s July 21st!!!! 💕🪩

DUA LIPA

892,056 просмотров • 3 лет назад

I'm oddly proud and stoked about this one - live video preview w/ audio of the Robotron AI training on the web. You can watch it live here: I started simple yesterday, a canvas I updated with a snapshot of the game that I pumped over a socket from an emulator session. That evolved into a video tag with a properly encoded video stream, and today I spent a full damned day almost adding audio and keeping it in sync with the game (which runs at an uncorked and unpredictable framerate). Assuming my machine can handle the load, it's available for viewing pleasure now at the link above :-) You have to click on the preview to enable the audio, and you can turn it off/on at the bottom of the page. Thanks to dsobeski for beta-testing it!

I'm oddly proud and stoked about this one - live video preview w/ audio of the Robotron AI training on the web. You can watch it live here: I started simple yesterday, a canvas I updated with a snapshot of the game that I pumped over a socket from an emulator session. That evolved into a video tag with a properly encoded video stream, and today I spent a full damned day almost adding audio and keeping it in sync with the game (which runs at an uncorked and unpredictable framerate). Assuming my machine can handle the load, it's available for viewing pleasure now at the link above :-) You have to click on the preview to enable the audio, and you can turn it off/on at the bottom of the page. Thanks to dsobeski for beta-testing it!

Dave W Plummer

15,271 просмотров • 6 месяцев назад

When people ask why I’m single and why I’m waiting on marriage to sleep with my husband here you go. My body belongs to God and until I meet my husband I’m not tainting it. My future babies and my future husband deserve it. I deserve it. My temple. Call me silly. I want the fairytale. And ladies you deserve the fairytale too. You know it’s never men that are shocked when I tell them this. It’s always women who are shocked. Ladies believe and hold on to the most precious thing you can give your husband. Don’t treat your body like it isn’t beautiful and valuable. Listen 🎧 ✡️✝️ #single #marriage #waiting

Sensitive content

When people ask why I’m single and why I’m waiting on marriage to sleep with my husband here you go. My body belongs to God and until I meet my husband I’m not tainting it. My future babies and my future husband deserve it. I deserve it. My temple. Call me silly. I want the fairytale. And ladies you deserve the fairytale too. You know it’s never men that are shocked when I tell them this. It’s always women who are shocked. Ladies believe and hold on to the most precious thing you can give your husband. Don’t treat your body like it isn’t beautiful and valuable. Listen 🎧 ✡️✝️ #single #marriage #waiting

Kaya Jones

521,455 просмотров • 2 лет назад

Most voice models are great at cloning voices, but they still manage to erase the person. I have an accent. Voice models don't know how to preserve it. Whenever I clone my voice, models get the words right, but mess up the rhythm badly. They flatten my vowels, and everything drifts toward a generic American accent. I'm attaching one example from Mirage. This is the first model I have heard of that can reproduce access as-is. • My accent stays intact, even when speaking English and Spanish • My pacing and cadence feel intentional, not averaged • The expressivity of my voice comes through Best part: Mirage only needs a short sample of your voice to clone it. I think this solves the hard part of voice cloning: intelligibility is easy, but identity is what makes a huge difference. Listen to the attached sample, and you'll notice the difference if you compare it with any other model out there. If you want to try this out, check out this link: Thanks to the Mirage team for collaborating with me on this post.

Most voice models are great at cloning voices, but they still manage to erase the person. I have an accent. Voice models don't know how to preserve it. Whenever I clone my voice, models get the words right, but mess up the rhythm badly. They flatten my vowels, and everything drifts toward a generic American accent. I'm attaching one example from Mirage. This is the first model I have heard of that can reproduce access as-is. • My accent stays intact, even when speaking English and Spanish • My pacing and cadence feel intentional, not averaged • The expressivity of my voice comes through Best part: Mirage only needs a short sample of your voice to clone it. I think this solves the hard part of voice cloning: intelligibility is easy, but identity is what makes a huge difference. Listen to the attached sample, and you'll notice the difference if you compare it with any other model out there. If you want to try this out, check out this link: Thanks to the Mirage team for collaborating with me on this post.

Santiago

32,044 просмотров • 9 месяцев назад

The Invenios Expeditions is coming soon! The second Leviathan Chronicles spin-off launches in just a few weeks, and it’s our most action-packed adventure yet. With nearly 100 voice actors, this is the biggest production we’ve ever done. We’ve put together a behind-the-scenes video to celebrate the journey. And if you want to hear it first, the Prologue, Operation Riverwolf, is now available on Patreon. 🎧 Listen now: #InveniosExpeditions #AudioDrama #Podcast #SciFi #LeviathanChronicles #fictionpodcasting

The Invenios Expeditions is coming soon! The second Leviathan Chronicles spin-off launches in just a few weeks, and it’s our most action-packed adventure yet. With nearly 100 voice actors, this is the biggest production we’ve ever done. We’ve put together a behind-the-scenes video to celebrate the journey. And if you want to hear it first, the Prologue, Operation Riverwolf, is now available on Patreon. 🎧 Listen now: #InveniosExpeditions #AudioDrama #Podcast #SciFi #LeviathanChronicles #fictionpodcasting

Leviathan Audio Productions

15,056 просмотров • 1 год назад

You do not need to listen to most podcasts anymore. I pasted a 2-hour interview into HypeScribe and got: • a full transcript • key takeaways • action items • a clean summary • answers from AI chat in under 5 minutes. The wild part: it works with YouTube, TikTok, Instagram, Zoom calls, voice memos, basically anything with audio. My current workflow: podcast/video → HypeScribe → summary → content ideas Way faster than rewatching everything manually. I’ve been using it to turn long-form content into threads, notes, and research without wasting hours. Feels less like “taking notes” and more like having an AI research assistant for everything you watch or record. If you work with content, meetings, research, or long videos, this is ridiculously useful. Try it here 👉🏻

You do not need to listen to most podcasts anymore. I pasted a 2-hour interview into HypeScribe and got: • a full transcript • key takeaways • action items • a clean summary • answers from AI chat in under 5 minutes. The wild part: it works with YouTube, TikTok, Instagram, Zoom calls, voice memos, basically anything with audio. My current workflow: podcast/video → HypeScribe → summary → content ideas Way faster than rewatching everything manually. I’ve been using it to turn long-form content into threads, notes, and research without wasting hours. Feels less like “taking notes” and more like having an AI research assistant for everything you watch or record. If you work with content, meetings, research, or long videos, this is ridiculously useful. Try it here 👉🏻

Onil Coder

12,075 просмотров • 3 месяцев назад

Walking back from a night out with the girls or walking back from spending the day at Disney theme park? I promise it was the 2nd one. It poured on us at Animal Kingdom and yall know I prefer to not wear shoes anyway. 1 arm is out because I was talking tattoos with another lady on the bus right before this. and if you listen close enough you can hear me losing my voice. That would be courtesy of universal studios not buckling my 6 year old properly into a ride and me screaming to stop the ride as soon as I found out.

Walking back from a night out with the girls or walking back from spending the day at Disney theme park? I promise it was the 2nd one. It poured on us at Animal Kingdom and yall know I prefer to not wear shoes anyway. 1 arm is out because I was talking tattoos with another lady on the bus right before this. and if you listen close enough you can hear me losing my voice. That would be courtesy of universal studios not buckling my 6 year old properly into a ride and me screaming to stop the ride as soon as I found out.

Honeybee

31,547 просмотров • 15 дней назад

BOOM! NEW GROKPOD UPDATE! I just stabilized my new Firehose AI output system! Using my RSVP technology and GrokPod with my AI router selected my local AI model to weigh in. This is the most powerful way to get the most information with the least effort, absolutely nothing comes close. With GrokPod you will get voice in and out and voice in to RSVP out, as well as other mixtures. Other than hacking in to your brain, this is the only way to keep up with AI outputs. It is a super power I built into this garage project. In the specimen video below the AI router detected the subject matter the local AI would be far more qualified to answer as I have 1000s of never seen documents on it. (If you know you know). With my RSVP technology you do not need to waste time and energy moving your eyes or randomly scanning that in many cases loses your place. More soon as I add the audio effect that aids in retention. No one else building AI devices have a clue about this including OpenAI and Apple. You and I have a clue and this is only what I will make public. Most of it is below the water line. There is far more. Iceberg strait ahead… More soon! And thank you for all of your support and kind words.

BOOM! NEW GROKPOD UPDATE! I just stabilized my new Firehose AI output system! Using my RSVP technology and GrokPod with my AI router selected my local AI model to weigh in. This is the most powerful way to get the most information with the least effort, absolutely nothing comes close. With GrokPod you will get voice in and out and voice in to RSVP out, as well as other mixtures. Other than hacking in to your brain, this is the only way to keep up with AI outputs. It is a super power I built into this garage project. In the specimen video below the AI router detected the subject matter the local AI would be far more qualified to answer as I have 1000s of never seen documents on it. (If you know you know). With my RSVP technology you do not need to waste time and energy moving your eyes or randomly scanning that in many cases loses your place. More soon as I add the audio effect that aids in retention. No one else building AI devices have a clue about this including OpenAI and Apple. You and I have a clue and this is only what I will make public. Most of it is below the water line. There is far more. Iceberg strait ahead… More soon! And thank you for all of your support and kind words.

Brian Roemmele

62,527 просмотров • 23 дней назад

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Google just shipped a free dictation app for Mac and iPhone called AI Edge Eloquent, and the model running it is Gemma 4 12B, entirely on your device. What it actually does: you speak, it transcribes, removes filler words, and polishes the result before dropping clean text into whatever app you are using. You can also give it voice commands to reformat, like "translate to Hindi" or "make this a bullet list." Audio and video file transcription is built in too. The interesting part is the privacy angle. Most AI writing tools send your audio to a server. This one never leaves your machine, which matters if you are dictating anything sensitive. The tradeoff is hardware: you need a Mac with at least 16GB of RAM to run a 12B parameter model comfortably.

Aditya ⚡Rao

85,093 просмотров • 3 месяцев назад

#BaiLu on choosing to dub Li Peiyi with her own voice “I’d like to talk a bit about the dubbing. It was mainly because of the filming environment in Hengdian there were a lot of noise issues. When we first started shooting this drama, the plan was to use the original on-set audio entirely. But as filming continued, the environmental interference became too much. We had a huge amount of dialogue every day, and eventually the director told us, ‘Forget it either you dub it yourselves in post-production, or we’ll bring in professional voice actors.’ By the end, voice actress Qiao Shiyu had already recorded my lines three times. She worked incredibly hard! Later on, though, the director messaged me on WeChat and said, ‘Lulu, come to the editing room. Don’t just listen on your phone listen in surround sound and then make your choice.’ Since this character is somewhat similar to my role in The Legends (Zhao Yao), Teacher Qiao Shiyu had dubbed it very diligently three times. In the end, I spent an entire afternoon in the editing room, and the whole team decided together that my natural voice might suit Pei Yi better. My voice isn’t perfect, and my delivery isn’t the absolute best, but perhaps for Pei Yi who isn’t meant to sound overly polished or perfectly ‘pretty’ my vocal tone fit the character more. So we ultimately chose to use my own voice. As actors, we know that using original audio is a real test of our abilities. We’ll keep working hard, and for any areas where I didn’t do well enough, I hope everyone can be understanding.”

#BaiLu on choosing to dub Li Peiyi with her own voice “I’d like to talk a bit about the dubbing. It was mainly because of the filming environment in Hengdian there were a lot of noise issues. When we first started shooting this drama, the plan was to use the original on-set audio entirely. But as filming continued, the environmental interference became too much. We had a huge amount of dialogue every day, and eventually the director told us, ‘Forget it either you dub it yourselves in post-production, or we’ll bring in professional voice actors.’ By the end, voice actress Qiao Shiyu had already recorded my lines three times. She worked incredibly hard! Later on, though, the director messaged me on WeChat and said, ‘Lulu, come to the editing room. Don’t just listen on your phone listen in surround sound and then make your choice.’ Since this character is somewhat similar to my role in The Legends (Zhao Yao), Teacher Qiao Shiyu had dubbed it very diligently three times. In the end, I spent an entire afternoon in the editing room, and the whole team decided together that my natural voice might suit Pei Yi better. My voice isn’t perfect, and my delivery isn’t the absolute best, but perhaps for Pei Yi who isn’t meant to sound overly polished or perfectly ‘pretty’ my vocal tone fit the character more. So we ultimately chose to use my own voice. As actors, we know that using original audio is a real test of our abilities. We’ll keep working hard, and for any areas where I didn’t do well enough, I hope everyone can be understanding.”

美

21,805 просмотров • 7 месяцев назад

The final surprise of AI April... I'm excited to announce the launch of Lenny's Reads—an audio podcast edition of Lenny’s Newsletter. Many of you have told me that you’d prefer to listen to my newsletter instead of read it. I’m excited to share that now you can. Every newsletter post will now be transformed into an audio podcast, read to you by the soothing voice of Lennybot. We’ll ship the podcast version of each post within 48 hours after it's published. Paid subscribers will hear the full post, and just like with the newsletter, free subscribers will get everything up to the paywall. For a limited time, the first five episodes of this new podcast will be completely unpaywalled and available to all listeners. Get on it. Listen now (and subscribe) here: - Spotify: - Apple: - YouTube: I’m excited to hear what you think.

The final surprise of AI April... I'm excited to announce the launch of Lenny's Reads—an audio podcast edition of Lenny’s Newsletter. Many of you have told me that you’d prefer to listen to my newsletter instead of read it. I’m excited to share that now you can. Every newsletter post will now be transformed into an audio podcast, read to you by the soothing voice of Lennybot. We’ll ship the podcast version of each post within 48 hours after it's published. Paid subscribers will hear the full post, and just like with the newsletter, free subscribers will get everything up to the paywall. For a limited time, the first five episodes of this new podcast will be completely unpaywalled and available to all listeners. Get on it. Listen now (and subscribe) here: - Spotify: - Apple: - YouTube: I’m excited to hear what you think.

Lenny Rachitsky

38,106 просмотров • 1 год назад

I have a speech impediment. Some days, I struggle to say my own name. I spoke to Matt Chorley about stammering, the impact it’s had on my life in politics and how I navigate it. It’s not always easy, but I won’t let it silence me. Stammerers are some of the bravest, most talented people I know. To young people with speech impediments thinking about getting into politics, my message is simple: go for it! Your voice deserves to be heard and there are so many of us here to support you Listen from 1:15:00 here:

I have a speech impediment. Some days, I struggle to say my own name. I spoke to Matt Chorley about stammering, the impact it’s had on my life in politics and how I navigate it. It’s not always easy, but I won’t let it silence me. Stammerers are some of the bravest, most talented people I know. To young people with speech impediments thinking about getting into politics, my message is simple: go for it! Your voice deserves to be heard and there are so many of us here to support you Listen from 1:15:00 here:

David Pinto-Duschinsky MP

10,507 просмотров • 7 месяцев назад

In the final stages of testing my Blender Compositor Line Art addon before release. Here's a look at how it works on a very high detail character. We have lines based on toon shading and vertex color ID groups. You can see it works very cleanly in some areas, but then runs into issues in others. That is because this mesh is complex but doesn't have smoothed normals yet, which causes the toon shading to create very small shaded areas that become lines. (We'll see it with Smoothed Normals next update.) This is the double-edged sword of this method, and any other Screen Space Extraction method, including the new Raycast Node: they are extremely precise, which allows very high detail and fine control, but also means you need to guard against bad inputs. But my toolset gives you full control over what data you create lines from, so you can ensure clean ID groups, run lines on different Normals than you shade with, mask at any stage, or anything else you need! And of course, most line methods (especially Inverted Hull) completely fail on complex or dirty geometry.

In the final stages of testing my Blender Compositor Line Art addon before release. Here's a look at how it works on a very high detail character. We have lines based on toon shading and vertex color ID groups. You can see it works very cleanly in some areas, but then runs into issues in others. That is because this mesh is complex but doesn't have smoothed normals yet, which causes the toon shading to create very small shaded areas that become lines. (We'll see it with Smoothed Normals next update.) This is the double-edged sword of this method, and any other Screen Space Extraction method, including the new Raycast Node: they are extremely precise, which allows very high detail and fine control, but also means you need to guard against bad inputs. But my toolset gives you full control over what data you create lines from, so you can ensure clean ID groups, run lines on different Normals than you shade with, mask at any stage, or anything else you need! And of course, most line methods (especially Inverted Hull) completely fail on complex or dirty geometry.

aVersionOfReality

17,063 просмотров • 5 месяцев назад

"What do you say about me spoiling you tonight? Celebrating you as the father figure my child adores and as the man I am hopelessly in love with and want to spend the rest of my life with." ❤️//💬//🔁 appreciated! Full 20 minute SFW cut free to listen on Fourthwall & Patreon 🎧🔗⤵️ — ✧ Your wife gives you a Father's Day surprise [F4M] [SFW cut] [playful] [intimate] She was a single mother when you got together. Now, years later, you're married, and she wants to celebrate Father's Day with you for the first time. 🏷️ Tags [romantic] [teasing] [setting the mood] [pillow talk] [surprise!] [give me your hand] [thank you for all you do] ✨ Names Used mister, smart boy, baby ─── ⋆⁺‧₊ ☾ ₊‧⁺⋆ ─── 💌 Note I thought up this audio when thinking about what it means to be a dad. And you guys know how much I love sweet and intimate audios.

"What do you say about me spoiling you tonight? Celebrating you as the father figure my child adores and as the man I am hopelessly in love with and want to spend the rest of my life with." ❤️//💬//🔁 appreciated! Full 20 minute SFW cut free to listen on Fourthwall & Patreon 🎧🔗⤵️ — ✧ Your wife gives you a Father's Day surprise [F4M] [SFW cut] [playful] [intimate] She was a single mother when you got together. Now, years later, you're married, and she wants to celebrate Father's Day with you for the first time. 🏷️ Tags [romantic] [teasing] [setting the mood] [pillow talk] [surprise!] [give me your hand] [thank you for all you do] ✨ Names Used mister, smart boy, baby ─── ⋆⁺‧₊ ☾ ₊‧⁺⋆ ─── 💌 Note I thought up this audio when thinking about what it means to be a dad. And you guys know how much I love sweet and intimate audios.

KimariRoseVA 🌙🥀

50,755 просмотров • 3 месяцев назад

Voice AI can pass a Turing test. For about a minute. That's a generated clip, though. Have a human actually talk back and the number collapses to six or seven seconds, roughly where generated voice sat three years ago. One reason: real conversation isn't turn-based. Around 20% of the time more than one person is speaking, and laughter drives a lot of that overlap, since you laugh at a joke while it's still being told. We also adjust our pacing toward whoever we're talking to without noticing we're doing it. Voice models struggle with all of this. Full-duplex voice, where a model listens and speaks at the same time, is still extremely early. So an agent can know your joke is funny and still have to wait until you've finished before it laughs, by which point the timing has killed it. Miso Labs CEO & Co-Founder, Aoden Teo, describes a second consequence: agents get pushed toward almost "psychotically emotive" behavior. If they can only talk once you've stopped, they need some other way to show they were listening. You finish your sentence, and the thing goes "Hmm?". You've heard it. Underneath that sits an architecture problem. Voice models have to respond fast, which constrains how large they can be, and fast means something different here than it does in text. Working with an LLM like Claude, you care how quickly it finishes your code, more than how quickly it starts. Voice inverts that. Nobody needs 10 hours of audio generated in two seconds, because nobody can listen to 10 hours of audio in two seconds; what matters is reaction time. Most architectural decisions trade latency against throughput, and Aoden expects voice to keep moving away from LLM-style designs toward ones built around very low latency. Miso Labs is already pushing on it. Miso-1 got 3,000+ stars on GitHub and 5 million views on X, and they record data in their own LA studio because the internet doesn't contain every kind of audio a voice model might need. Nobody has released a podcast of someone reading millions and millions of email addresses, and people still want voice models that can read email addresses aloud, so teams end up generating some very strange training data themselves. The clip isn't the hard part. The hard part starts when you talk back. "The most emotive foundation models for voice" 🎙️Aoden Teo, CEO & Co-Founder, Miso Labs on Fondo.com START 1:03 Miso-1: 3K+ GitHub stars + 5M X views 1:59 Why emotiveness matters for games, UGC + interactive products 3:06 Measuring progress in voice AI with longer Turing tests 4:01 Why interactive conversation is harder than generating convincing clips 5:08 Full-duplex voice, interruptions + why laughter matters 6:04 Latency vs. throughput - and why voice differs from LLMs 7:09 Miso's LA recording studio + the challenge of voice training data 9:02 Talking teddy bears, UGC, anime + unexpected voice AI use cases 10:19 From serious chess player to math obsession to building Miso Labs 12:11 The surprise YC interview

Voice AI can pass a Turing test. For about a minute. That's a generated clip, though. Have a human actually talk back and the number collapses to six or seven seconds, roughly where generated voice sat three years ago. One reason: real conversation isn't turn-based. Around 20% of the time more than one person is speaking, and laughter drives a lot of that overlap, since you laugh at a joke while it's still being told. We also adjust our pacing toward whoever we're talking to without noticing we're doing it. Voice models struggle with all of this. Full-duplex voice, where a model listens and speaks at the same time, is still extremely early. So an agent can know your joke is funny and still have to wait until you've finished before it laughs, by which point the timing has killed it. Miso Labs CEO & Co-Founder, Aoden Teo, describes a second consequence: agents get pushed toward almost "psychotically emotive" behavior. If they can only talk once you've stopped, they need some other way to show they were listening. You finish your sentence, and the thing goes "Hmm?". You've heard it. Underneath that sits an architecture problem. Voice models have to respond fast, which constrains how large they can be, and fast means something different here than it does in text. Working with an LLM like Claude, you care how quickly it finishes your code, more than how quickly it starts. Voice inverts that. Nobody needs 10 hours of audio generated in two seconds, because nobody can listen to 10 hours of audio in two seconds; what matters is reaction time. Most architectural decisions trade latency against throughput, and Aoden expects voice to keep moving away from LLM-style designs toward ones built around very low latency. Miso Labs is already pushing on it. Miso-1 got 3,000+ stars on GitHub and 5 million views on X, and they record data in their own LA studio because the internet doesn't contain every kind of audio a voice model might need. Nobody has released a podcast of someone reading millions and millions of email addresses, and people still want voice models that can read email addresses aloud, so teams end up generating some very strange training data themselves. The clip isn't the hard part. The hard part starts when you talk back. "The most emotive foundation models for voice" 🎙️Aoden Teo, CEO & Co-Founder, Miso Labs on Fondo.com START 1:03 Miso-1: 3K+ GitHub stars + 5M X views 1:59 Why emotiveness matters for games, UGC + interactive products 3:06 Measuring progress in voice AI with longer Turing tests 4:01 Why interactive conversation is harder than generating convincing clips 5:08 Full-duplex voice, interruptions + why laughter matters 6:04 Latency vs. throughput - and why voice differs from LLMs 7:09 Miso's LA recording studio + the challenge of voice training data 9:02 Talking teddy bears, UGC, anime + unexpected voice AI use cases 10:19 From serious chess player to math obsession to building Miso Labs 12:11 The surprise YC interview

David J Phillips

36,612 просмотров • 22 дней назад

Learn to build conversational AI voice agents in "Building AI Voice Agents for Production", created in collaboration with LiveKit and RealAvatar, and taught by dsa (Co-founder & CEO of LiveKit), Shayne (Developer Advocate, LiveKit), and Nedelina Teneva (Head of AI at RealAvatar, an AI Fund portfolio company). Voice agents combine speech and reasoning capabilities to enable real-time conversations. They're already being used to support customer service, to improve accessibility in healthcare, for entertainment applications, and for talk therapy. In this course, you’ll learn to build voice agents that listen, reason, and respond naturally. You’ll follow the architecture used to create the "AI Andrew" Avatar, a collaborative project between and RealAvatar that responds to users in what sounds like my voice. You’ll build a voice agent from scratch and deploy it to the cloud, enabling support for many simultaneous users. What you’ll learn: - Understand the fundamentals of voice agents, including key components like speech-to-text (STT), text-to-speech (TTS), and LLMs, and how latency is introduced at each layer. - Explore voice agent architectures and the trade-offs between modular pipelines and speech-to-speech APIs. - Explore how platforms like LiveKit mitigate latency issues with optimized networking infrastructure and low-latency communication protocols. - Learn how to connect client devices to voice agents using WebRTC—and why it outperforms HTTP and WebSocket for low-latency audio streaming. - Incorporate voice activity detection (VAD), end-of-turn detection, and context management to detect turns, handle interruptions, and manage conversational flow. - Understand the trade-offs between latency, quality, and cost in an example in which you build a voice agent and change its voice. - Equip your agent with metrics to measure latency at each stage of the voice pipeline and learn the key levers you can pull to make your agent faster and more responsive. The voice agents built in this course also incorporate voice technology from , a supporting contributor to the project. By the end of this course, you'll have learned the components of an AI voice agent pipeline, combined them into a system with low-latency communication, and deployed them on cloud infrastructure so it scales to many users. I’m looking forward to seeing what voice agents you build from this course! Please sign up here:

Andrew Ng

87,868 просмотров • 1 год назад

📣Teachers and librarians! 📣 I’ve created a new FREE writing curriculum for classrooms called Write With FRONT DESK! 🙌 Packed w videos, lesson plans and PowerPoints on metaphors, personification and so much more—it’s all free and downloadable at the link in my bio! I made it with my dear friend Molly Callender, an award winning elementary school teacher! 🤩We’re so excited for kids to learn to write with the FRONT DESK series, alongside Mia Tang! 😍 Every unit comes with a video from me showing kids how I use literary devices in my own writing! It’s super FUN, relatable, and most of all, empowering! Because every child deserves to find their voice, as I did when I was a young, immigrant girl! 🥹 It literally changed my life and I wouldn’t be here if it weren’t for my amazing teachers and librarians—so today, it’s my turn to give back! Together, let’s inspire as many kids to find their voice as we can! As always, thank you for what you do—you’re changing lives!!! ✍️❤️📚 #FrontDeskSeries #WriteWithFrontDesk #MiaTang #Writing #FreeCurriculum #KellyYang #Teachers #Librarians

📣Teachers and librarians! 📣 I’ve created a new FREE writing curriculum for classrooms called Write With FRONT DESK! 🙌 Packed w videos, lesson plans and PowerPoints on metaphors, personification and so much more—it’s all free and downloadable at the link in my bio! I made it with my dear friend Molly Callender, an award winning elementary school teacher! 🤩We’re so excited for kids to learn to write with the FRONT DESK series, alongside Mia Tang! 😍 Every unit comes with a video from me showing kids how I use literary devices in my own writing! It’s super FUN, relatable, and most of all, empowering! Because every child deserves to find their voice, as I did when I was a young, immigrant girl! 🥹 It literally changed my life and I wouldn’t be here if it weren’t for my amazing teachers and librarians—so today, it’s my turn to give back! Together, let’s inspire as many kids to find their voice as we can! As always, thank you for what you do—you’re changing lives!!! ✍️❤️📚 #FrontDeskSeries #WriteWithFrontDesk #MiaTang #Writing #FreeCurriculum #KellyYang #Teachers #Librarians

Kelly Yang

12,116 просмотров • 2 лет назад