Video wird geladen...

Video konnte nicht geladen werden

Zur Startseite

Surprised there isn't more chatter around VALL-E This new model by Microsoft can generate speech in any voice after only hearing a 3s sample of that voice 🤯 Demo →

steventey's profile picture

Steven Tey

58,274 subscribers

705,819 Aufrufe • vor 3 Jahren •via X (Twitter)

BildungWissenschaft & TechnologieNachrichten & Politik
LIVE

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

SeamlessExpressive, a new AI translation model by research teams at Meta, enables high-quality speech translation that maintains the speaker's vocal style, tone and unique expressions in translated outputs. Try the demo with your own voice ➡️
0:14

SeamlessExpressive, a new AI translation model by research teams at Meta, enables high-quality speech translation that maintains the speaker's vocal style, tone and unique expressions in translated outputs. Try the demo with your own voice ➡️

AI at Meta

169,032 Aufrufe • vor 2 Jahren

Introducing smalltts, a new ultrafast text-to-speech model • generates ~15s of audio instantly on a laptop • clone any voice • laugh, cry, groan, cough, & more open source. available via x402 api for 1 cent a minute
0:11

Introducing smalltts, a new ultrafast text-to-speech model • generates ~15s of audio instantly on a laptop • clone any voice • laugh, cry, groan, cough, & more open source. available via x402 api for 1 cent a minute

Small Brain

48,549 Aufrufe • vor 6 Monaten

wow... this new AI is incredible. Kaiber AI just dropped film Superstudio Pro, a node based canvas that can generate storyboard, video, voice, sfx(MMAudio) and even... train character, object, place and style all in one page step by step tutorial:
0:12

wow... this new AI is incredible. Kaiber AI just dropped film Superstudio Pro, a node based canvas that can generate storyboard, video, voice, sfx(MMAudio) and even... train character, object, place and style all in one page step by step tutorial:

el.cine

325,597 Aufrufe • vor 1 Jahr

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.
0:17

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Akshay 🚀

31,249 Aufrufe • vor 6 Monaten

This is not just a serious slander against His Holiness the Dalai Lama alone! This is not just a slander to the Tibetan nation! We can watch. There is not only one voice in this world, nor is there only one culture, nor is there only one kind of power.
0:16

This is not just a serious slander against His Holiness the Dalai Lama alone! This is not just a slander to the Tibetan nation! We can watch. There is not only one voice in this world, nor is there only one culture, nor is there only one kind of power.

Sangyal Kunchok (སངས་རྒྱས།) 💎

33,223 Aufrufe • vor 3 Jahren

john prescott dissociating at the 1997 election victory when all of a sudden he hears this agitating grating voice peter mandelson. neil kinnock is also there dancing to things can only get better new labour anthem robin cook
0:10

john prescott dissociating at the 1997 election victory when all of a sudden he hears this agitating grating voice peter mandelson. neil kinnock is also there dancing to things can only get better new labour anthem robin cook

uk politics reaction video

169,407 Aufrufe • vor 2 Monaten

One of the issues for Kentucky is that there are few, if any, real answers when an "easy" bucket is needed. If it isn't something that Coach Pope can draw up in a timeout there just isn't a "go-to" option. THIS is what the 'Cats got in response to an Auburn "Kill Shot."
0:10

One of the issues for Kentucky is that there are few, if any, real answers when an "easy" bucket is needed. If it isn't something that Coach Pope can draw up in a timeout there just isn't a "go-to" option. THIS is what the 'Cats got in response to an Auburn "Kill Shot."

Brandon Ramsey

33,626 Aufrufe • vor 5 Monaten

GOOGLE 🔥: An upcoming Gemini Omni video model from Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀
0:10

GOOGLE 🔥: An upcoming Gemini Omni video model from Google is expected to be much more advanced in video editing, capable of completing tasks like removing watermarks, replacing objects in the video, and more. It is also likely that Google will release 2 versions of this model, including a Pro variant. And I assume what we see isn't Pro? Anime sample 👀

🚨 AI News | TestingCatalog

179,938 Aufrufe • vor 3 Monaten

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵
0:12

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: 🧵

Carl Doersch

45,265 Aufrufe • vor 1 Jahr

First Sora 2 Pro generation 👀 This upgraded model is available on the website only. It takes several times longer to generate and can produce higher resolution videos. Prompt: cute female anime streamer navigating through a game. suddenly, her voice changes to a husky man. then the stream glitches out and she's replaced by the man, who is embarrassed.
0:10

First Sora 2 Pro generation 👀 This upgraded model is available on the website only. It takes several times longer to generate and can produce higher resolution videos. Prompt: cute female anime streamer navigating through a game. suddenly, her voice changes to a husky man. then the stream glitches out and she's replaced by the man, who is embarrassed.

Justine Moore

25,456 Aufrufe • vor 10 Monaten

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.
0:18

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.

Hume AI

24,684 Aufrufe • vor 4 Monaten

🚨BREAKING🚨 Alberta Independence supporter is attacked in Edmonton Alberta waving his Alberta Flag! Not only that he is almost ran over by a car! This is getting out of hand! It’s a question and all Albertans deserve a voice… Those on the yes side vote yes! And those in the no side vote no! I hope this violence doesn’t escalate and we can all have a voice on October 19th!
0:16

🚨BREAKING🚨 Alberta Independence supporter is attacked in Edmonton Alberta waving his Alberta Flag! Not only that he is almost ran over by a car! This is getting out of hand! It’s a question and all Albertans deserve a voice… Those on the yes side vote yes! And those in the no side vote no! I hope this violence doesn’t escalate and we can all have a voice on October 19th!

BertaProudDad

35,983 Aufrufe • vor 1 Monat

✨ I updated Photo AI's video model to Kling AI 2.6 now By default it also generates audio (like Veo 3 does) and if you prompt for it it also produces voice, and it's pretty realistic too I'd say the cadence of the voice can be improved to be a bit more real, but it's definitely getting there It's just one click, just generate an AI photo first then hover over it and press [ 📼 Make video ] It's 3x more expensive, but I sell it below cost (5 credits) so that you all sign up to Photo AI and generate your UGC influencers with me 😊 Here's my 100% AI influencer telling what she thinks of the European Commission
0:10

✨ I updated Photo AI's video model to Kling AI 2.6 now By default it also generates audio (like Veo 3 does) and if you prompt for it it also produces voice, and it's pretty realistic too I'd say the cadence of the voice can be improved to be a bit more real, but it's definitely getting there It's just one click, just generate an AI photo first then hover over it and press [ 📼 Make video ] It's 3x more expensive, but I sell it below cost (5 credits) so that you all sign up to Photo AI and generate your UGC influencers with me 😊 Here's my 100% AI influencer telling what she thinks of the European Commission

@levelsio

323,674 Aufrufe • vor 8 Monaten

This free GitHub fork can get you to $5,000/month. Clones any voice for free, writes the script, makes the video. Zero API costs, zero camera. It's MoneyPrinterTurbo Extended - an enhanced fork of the repo that already prints faceless content on autopilot. This version closes the last paid gap: voice. >> What's new in this fork: - Chatterbox TTS built in - completely free voice cloning, no API costs, no rate limits. - Clone any voice from 10-60 seconds of reference audio. - Word-by-word subtitle highlighting that lights up exactly when spoken. - Semantic video matching - pulls clips that actually match the script's meaning instead of random stock footage. Same pipeline as before: topic in, script out, voiceover generated, footage matched, subtitles synced, finished video. The difference is now nothing in the chain costs money. Script generation, voice, footage, editing - all free, all local. // This is the exact setup behind faceless channels pulling $800-3,000+/month once they scale. Run multiple channels in parallel, multiple niches, and the free voice cloning alone removes the biggest recurring cost most people are still paying for. Repo: Open source. MIT license. Bookmark this before you lose the repo.
0:15

This free GitHub fork can get you to $5,000/month. Clones any voice for free, writes the script, makes the video. Zero API costs, zero camera. It's MoneyPrinterTurbo Extended - an enhanced fork of the repo that already prints faceless content on autopilot. This version closes the last paid gap: voice. >> What's new in this fork: - Chatterbox TTS built in - completely free voice cloning, no API costs, no rate limits. - Clone any voice from 10-60 seconds of reference audio. - Word-by-word subtitle highlighting that lights up exactly when spoken. - Semantic video matching - pulls clips that actually match the script's meaning instead of random stock footage. Same pipeline as before: topic in, script out, voiceover generated, footage matched, subtitles synced, finished video. The difference is now nothing in the chain costs money. Script generation, voice, footage, editing - all free, all local. // This is the exact setup behind faceless channels pulling $800-3,000+/month once they scale. Run multiple channels in parallel, multiple niches, and the free voice cloning alone removes the biggest recurring cost most people are still paying for. Repo: Open source. MIT license. Bookmark this before you lose the repo.

Atenov int.

39,712 Aufrufe • vor 2 Monaten

Since there's new voice lines. 🦁 Its a big help having a hardworker like you around. Thanks to that, I can just kick back and take it easy like this. (I swear Savanaclaw has been harassing me two weeks in my logins. I feel like Azul rn 😭)
0:14

Since there's new voice lines. 🦁 Its a big help having a hardworker like you around. Thanks to that, I can just kick back and take it easy like this. (I swear Savanaclaw has been harassing me two weeks in my logins. I feel like Azul rn 😭)

Doom 🪸 CEO of Azul

26,909 Aufrufe • vor 5 Monaten

Listen closely to this segment of BTS's performance at the World Cup final show. When Kim Taehyung enters, his voice takes on a much greater spatial presence. It is as if his voice “takes over” the stadium. Although the vocalists share the melodic line, Taehyung's entry immediately alters the spatial perception of the performance. This week, alongside other vocal professionals, I was exploring the concept of “DOMINANT TIMBRE.” While not a formal technical term in vocal acoustics, it is frequently used to describe voices whose timbral identity naturally stands out within an ensemble. In terms of social perception — specifically in behavioral and communication studies — the term can also describe vocal tones that convey authority, power, or dominance. This perception can be explained by a combination of factors related to vocal projection, the harmonic spectrum, resonance, and acoustic presence. The result is a voice that seems to fill the stadium. V's voice possesses: • Greater vocal projection: the voice seems to “travel” effortlessly across the stadium. • More energy in the mid-high harmonics (singer's formant): this region of the spectrum allows a voice to stand out, even in a massive venue. • Highly efficient resonance: the vocal tract is configured so that the sound gains body and depth. • Greater “acoustic presence”: the voice seems to occupy more three-dimensional space, whereas other voices sound more localized. This explains why two people can sing the exact same pitch, at the same intensity (measured in dB), and the same melody, yet one of them seems “three times larger.” The brain interprets this voice as having more presence because it contains more acoustic information within the frequency ranges to which we are most sensitive. TAEHYUNG AT FIFA HALFTIME SHOW #Kimtaehyung #Taehyung #V #BTSV
0:17

Listen closely to this segment of BTS's performance at the World Cup final show. When Kim Taehyung enters, his voice takes on a much greater spatial presence. It is as if his voice “takes over” the stadium. Although the vocalists share the melodic line, Taehyung's entry immediately alters the spatial perception of the performance. This week, alongside other vocal professionals, I was exploring the concept of “DOMINANT TIMBRE.” While not a formal technical term in vocal acoustics, it is frequently used to describe voices whose timbral identity naturally stands out within an ensemble. In terms of social perception — specifically in behavioral and communication studies — the term can also describe vocal tones that convey authority, power, or dominance. This perception can be explained by a combination of factors related to vocal projection, the harmonic spectrum, resonance, and acoustic presence. The result is a voice that seems to fill the stadium. V's voice possesses: • Greater vocal projection: the voice seems to “travel” effortlessly across the stadium. • More energy in the mid-high harmonics (singer's formant): this region of the spectrum allows a voice to stand out, even in a massive venue. • Highly efficient resonance: the vocal tract is configured so that the sound gains body and depth. • Greater “acoustic presence”: the voice seems to occupy more three-dimensional space, whereas other voices sound more localized. This explains why two people can sing the exact same pitch, at the same intensity (measured in dB), and the same melody, yet one of them seems “three times larger.” The brain interprets this voice as having more presence because it contains more acoustic information within the frequency ranges to which we are most sensitive. TAEHYUNG AT FIFA HALFTIME SHOW #Kimtaehyung #Taehyung #V #BTSV

Music Map ⓥ

19,977 Aufrufe • vor 1 Monat