Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

introducing silk - the most expressive hinglish voice model by rumik 🐛 trained to laugh, be shocked, can pause, cough, whisper and sing a bit too :) try silk yourself -

lets_dig_deeper's profile picture

rohan

4,410 subscribers

66,413 görüntüleme • 6 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

an audio model that can switch languages, accents, tone, gender, emotions in a single instance this is silk mulberry 1.5 our most cost efficient model! by rumik research lab
1:03

an audio model that can switch languages, accents, tone, gender, emotions in a single instance this is silk mulberry 1.5 our most cost efficient model! by rumik research lab

rohan

58,311 görüntüleme • 3 ay önce

Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.
8:06

Introducing Empathic Voice Interface 2 (EVI 2), our new voice-to-voice foundation model. EVI 2 merges language and voice into a single model trained specifically for emotional intelligence. You can try it and start building today.

Hume AI

165,645 görüntüleme • 1 yıl önce

Here's your Friday Indian tech white pill: 1. rumik soft launched a voice model, silk 1, and it's shockingly good 2. Prava partnered with Visa to enable card-based agentic payments 3. newtonschooloftechnology has multiple team qualifying for the 2026 ICPC Asia West regionals
2:58

Here's your Friday Indian tech white pill: 1. rumik soft launched a voice model, silk 1, and it's shockingly good 2. Prava partnered with Visa to enable card-based agentic payments 3. newtonschooloftechnology has multiple team qualifying for the 2026 ICPC Asia West regionals

Runtime

23,857 görüntüleme • 6 ay önce

We added 600+ new voices on Together AI! Introducing MiniMax Speech 2.8 Turbo on Together AI, an enterprise TTS model for expressive real-time voice agents. AI natives can now deploy MiniMax (official) Speech 2.8 Turbo on Together AI dedicated infrastructure, and try the voices directly in voice finder.
0:37

We added 600+ new voices on Together AI! Introducing MiniMax Speech 2.8 Turbo on Together AI, an enterprise TTS model for expressive real-time voice agents. AI natives can now deploy MiniMax (official) Speech 2.8 Turbo on Together AI dedicated infrastructure, and try the voices directly in voice finder.

Together AI

21,814 görüntüleme • 3 ay önce

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.
4:03

Introducing GPT-Realtime-2 in the API: our most intelligent voice model yet, bringing GPT-5-class reasoning to voice agents. Voice agents are now real-time collaborators that can listen, reason, and solve complex problems as conversations unfold. Now available in the API alongside streaming models GPT-Realtime-Translate and GPT-Realtime-Whisper — a new set of audio capabilities for the next generation of voice interfaces.

OpenAI

3,661,990 görüntüleme • 3 ay önce

Traditionally, #RakshaBandhan was a time to strengthen the bond between brother and sister by using an energized thread. A non-sanforized cotton or non-chemically-treated silk thread can be energized to create a certain sense of security and stability in the system. -Sg
0:50

Traditionally, #RakshaBandhan was a time to strengthen the bond between brother and sister by using an energized thread. A non-sanforized cotton or non-chemically-treated silk thread can be energized to create a certain sense of security and stability in the system. -Sg

Sadhguru

44,592 görüntüleme • 2 yıl önce

Women queue up from 4.00 AM outside a Karnataka Soviet (sorry Silk) Industries Corporation showroom to buy silk sarees starting from ₹23,000 and going up to ₹250,000. Only 1 saree per customer and you need a token to be in the queue. There is an ongoing shortage (or more precisely, a supply shortfall) of authentic Mysore silk sarees, particularly those produced by the Karnataka Silk Industries Corporation, which holds the official production and GI-tagged rights for pure Mysore silk sarees. This has been a consistent issue throughout 2025, with no clear indication of resolution into 2026. First up, the Corporation has a limited number of skilled in-house weavers and artisans. Their training takes 6-7 months for even basic proficiency. Production is restricted to the Corporation's trained workforce and facilities, preventing rapid scaling. Seasonal peaks (weddings, Varalakshmi Puja, Gowri Ganesha, Deepavali) worsen the crunch, with showrooms often selling out quickly. This is how life was in the Soviet Union, which was plagued by shortages of almost everything except bread. But in fairness to the Corporation, at least authenticity is ensured. In contrast, private sector companies are known to cheat customers through spurious or Chinese made artificial silk. Illustrated by what happened at Tirupati where a private contractor was supplying fake silk to devotees.
0:34

Women queue up from 4.00 AM outside a Karnataka Soviet (sorry Silk) Industries Corporation showroom to buy silk sarees starting from ₹23,000 and going up to ₹250,000. Only 1 saree per customer and you need a token to be in the queue. There is an ongoing shortage (or more precisely, a supply shortfall) of authentic Mysore silk sarees, particularly those produced by the Karnataka Silk Industries Corporation, which holds the official production and GI-tagged rights for pure Mysore silk sarees. This has been a consistent issue throughout 2025, with no clear indication of resolution into 2026. First up, the Corporation has a limited number of skilled in-house weavers and artisans. Their training takes 6-7 months for even basic proficiency. Production is restricted to the Corporation's trained workforce and facilities, preventing rapid scaling. Seasonal peaks (weddings, Varalakshmi Puja, Gowri Ganesha, Deepavali) worsen the crunch, with showrooms often selling out quickly. This is how life was in the Soviet Union, which was plagued by shortages of almost everything except bread. But in fairness to the Corporation, at least authenticity is ensured. In contrast, private sector companies are known to cheat customers through spurious or Chinese made artificial silk. Illustrated by what happened at Tirupati where a private contractor was supplying fake silk to devotees.

Rakesh Krishnan Simha

513,969 görüntüleme • 7 ay önce

It's official – Bland Speech v3 is the world's most realistic voice model according to @designarena Hear what Matthew and Karen have to say on the topic 👇 Try it yourself for free at
0:49

It's official – Bland Speech v3 is the world's most realistic voice model according to @designarena Hear what Matthew and Karen have to say on the topic 👇 Try it yourself for free at

Bland

543,929 görüntüleme • 23 gün önce

🎬 PARDON ME: The Bevelyn B. Williams Story Premieres Today and Silk is helping bring it to the nation. “This movie is dear to my heart,” Silk from Diamond and Silk® told LindellTV. “ Bevelyn Williams was sentenced to 41 months in prison - the first Black woman ever charged under the FACE Act. And this film gives her the chance to tell the truth.” Funded entirely by Silk herself, the film features Angela White (Blac Chyna), Columbus Short, Jason Mitchell, Rampage Jackson and Silk in a cameo role. “This wasn’t just a little iPhone movie. It’s a full Hollywood production. And I paid for it myself because the truth matters and they don’t want you to see it.” Despite major theaters rejecting the film (Silk says many are tied to Planned Parenthood), churches across the country are stepping up to host screenings. “This movie is about faith, truth, and standing up for the unborn. That’s why they tried to censor it. But it’s too important not to share.” Watch now →
7:10

🎬 PARDON ME: The Bevelyn B. Williams Story Premieres Today and Silk is helping bring it to the nation. “This movie is dear to my heart,” Silk from Diamond and Silk® told LindellTV. “ Bevelyn Williams was sentenced to 41 months in prison - the first Black woman ever charged under the FACE Act. And this film gives her the chance to tell the truth.” Funded entirely by Silk herself, the film features Angela White (Blac Chyna), Columbus Short, Jason Mitchell, Rampage Jackson and Silk in a cameo role. “This wasn’t just a little iPhone movie. It’s a full Hollywood production. And I paid for it myself because the truth matters and they don’t want you to see it.” Despite major theaters rejecting the film (Silk says many are tied to Planned Parenthood), churches across the country are stepping up to host screenings. “This movie is about faith, truth, and standing up for the unborn. That’s why they tried to censor it. But it’s too important not to share.” Watch now →

LindellTV

35,504 görüntüleme • 7 ay önce

xAI just dropped 2 absolute monsters: Grok Speech-to-Text + Grok Text-to-Speech APIs Same battle-tested stack that runs Grok Voice, millions of Tesla cars, and Starlink support. - STT: Real-time WebSocket, speaker diarization, 25+ languages, word-level timestamps. - TTS: Super natural, expressive voices with tags for laugh, sigh, whisper, emphasis, pause; batch + streaming. Put voice AI on the list of things Grok already 100%'d xAI, Grok
0:27

xAI just dropped 2 absolute monsters: Grok Speech-to-Text + Grok Text-to-Speech APIs Same battle-tested stack that runs Grok Voice, millions of Tesla cars, and Starlink support. - STT: Real-time WebSocket, speaker diarization, 25+ languages, word-level timestamps. - TTS: Super natural, expressive voices with tags for laugh, sigh, whisper, emphasis, pause; batch + streaming. Put voice AI on the list of things Grok already 100%'d xAI, Grok

Mario Nawfal

164,897 görüntüleme • 4 ay önce

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊
2:13

Introducing Soniox TTS v2, our most powerful text-to-speech model yet. Soniox TTS v2 brings extraordinary voice quality, expressive control through audio tags, exceptional precision, high-fidelity voice cloning, more than 60 languages, natural language mixing, and low-latency streaming together in one model. Built from the ground up with a new model architecture, audio codec, and highly optimized inference engine, Soniox TTS v2 delivers frontier TTS at just $0.70 per generated hour. Available globally today as tts-rt-v2. Try it out: Turn the sound on and hear what’s possible. 🔊

Soniox

644,246 görüntüleme • 17 gün önce

Most men talk themselves out of attraction. Trying to be witty. Trying to be impressive. Trying too hard. That’s the problem. Less talking is sexier. A pause, a look, a shrug > a forced “clever” line. Silence signals confidence. Try-hard energy signals neediness. Women can tell instantly.
2:19

Most men talk themselves out of attraction. Trying to be witty. Trying to be impressive. Trying too hard. That’s the problem. Less talking is sexier. A pause, a look, a shrug > a forced “clever” line. Silence signals confidence. Try-hard energy signals neediness. Women can tell instantly.

FortWorthPlayboy

11,583 görüntüleme • 5 ay önce

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)
0:52

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)

rumik

30,786 görüntüleme • 1 ay önce

By the stone-paved paths of the ancient town, the gentle sound of silk and bamboo begins to flow. The guzheng, pipa, and flute harmonize as one. In this moment, time seems to slow down— Music is not only played, but felt. And in that moment, you might realize: life can be soft and tender too. From Yancheng Cultural Center
1:44

By the stone-paved paths of the ancient town, the gentle sound of silk and bamboo begins to flow. The guzheng, pipa, and flute harmonize as one. In this moment, time seems to slow down— Music is not only played, but felt. And in that moment, you might realize: life can be soft and tender too. From Yancheng Cultural Center

Discover Yancheng

116,807 görüntüleme • 10 ay önce

“The more you can be yourself, the most authentic version of yourself, the more well you’re going to be received by your players and the other people you work with” OC Steve Cooper
0:47

“The more you can be yourself, the most authentic version of yourself, the more well you’re going to be received by your players and the other people you work with” OC Steve Cooper

UCF Football

11,147 görüntüleme • 1 yıl önce

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.
0:52

Voice Design v3 is here. Create any voice you can imagine with a prompt. We’ve rebuilt the underlying Voice Design model to deliver higher quality and broader expressive range. Generate production-ready voices in 70+ languages with support for hundreds of localized accents.

ElevenLabs

153,990 görüntüleme • 1 yıl önce

Introducing canvas—your coding surface in ChatGPT. ✏️ Edit code inline 🐛 Review code and fix bugs 💬 Add logs and comments 🚢 Port to different languages We’ll be adding more to canvas over time. ChatGPT Plus and Team users can try the beta starting today.
1:30

Introducing canvas—your coding surface in ChatGPT. ✏️ Edit code inline 🐛 Review code and fix bugs 💬 Add logs and comments 🚢 Port to different languages We’ll be adding more to canvas over time. ChatGPT Plus and Team users can try the beta starting today.

OpenAI Developers

934,987 görüntüleme • 1 yıl önce