正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Meta AI is on fire. They just announced Voicebox, a multilingual high-quality text-to-speech AI. The quality is so good that they're not making the Voicebox model or code publicly available (yet) to avoid misuse. Sounds like it's about to go compete with ElevenLabs/PlayHT.

Rowan Cheung

594,225 subscribers

323,029 次观看 • 3 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Rowan Cheung 的头像

Rowan Cheung3 年前

Going more in-depth on this in tomorrow's newsletter:

Ed 🌹 的头像

Ed 🌹3 年前

2.5 year partnership, mostly guarded by an NDA. Founded by Dawn Song, the most cited scholar in computer science and #AI Probably nothing.. $ROSE 🌹

Jeremy Nguyen ✍🏼 🚢 的头像

Jeremy Nguyen ✍🏼 🚢3 年前

Uh oh. A lot of elderly parents are going to be getting phone calls from "their children" who are stuck at the airport and need some money transferred.

Rowan Cheung 的头像

Rowan Cheung3 年前

I’ve heard of this happening already. The world needs to be educated ASAP on the risks associated with AI voice + cloning

Alvaro Cintas 的头像

Alvaro Cintas3 年前

Completely agree! Meta is crushing it on AI.

Rowan Cheung 的头像

Rowan Cheung3 年前

Their pace of development is incredible

Margot 的头像

Margot3 年前

Is it possible to make whole AI semi auto NFT being?

Min Choi 的头像

Min Choi3 年前

Meta AI has been really firing it up 🔥

Mike Lazarus 的头像

Mike Lazarus3 年前

I’m waiting for the first good vocal software to bring back dead artists. This might be it. I want to hear Michael Jackson cover Blinding Lights.

AI University 的头像

AI University3 年前

Meta is going ham

相关视频

AMGI is proud to be partnering with ElevenLabs 🤝 ElevenLabs is the premier AI speech synthesis company in the space. Recognized as a major contributor to the ongoing AI boom, this exciting partnership ensures our ability to make the highest quality AI integrated products.

AMGI is proud to be partnering with ElevenLabs 🤝 ElevenLabs is the premier AI speech synthesis company in the space. Recognized as a major contributor to the ongoing AI boom, this exciting partnership ensures our ability to make the highest quality AI integrated products.

AMGI Studios

94,417 次观看 • 2 年前

At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech - a new model architecture that delivers human-level quality on limited hardware without an internet connection.

At the ElevenLabs Summit in Warsaw, we previewed on-device Text to Speech - a new model architecture that delivers human-level quality on limited hardware without an internet connection.

ElevenLabs

35,091 次观看 • 2 个月前

Our Reader App is now available worldwide on iOS and Android. Listen to any book, article, PDF or text on the go in hundreds of high quality AI voices. Now in 32 languages. It’s completely free to download and use. Find it on iOS and Android here:

Our Reader App is now available worldwide on iOS and Android. Listen to any book, article, PDF or text on the go in hundreds of high quality AI voices. Now in 32 languages. It’s completely free to download and use. Find it on iOS and Android here:

ElevenLabs

588,351 次观看 • 1 年前

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

Introducing Eleven Multilingual v2: our new AI speech model supporting 28 languages! v2 comes with enhanced conversational capability, higher output quality & the ability to better preserve unique voice characteristics across languages. Read more:

ElevenLabs

293,421 次观看 • 2 年前

Open-source project Soundstorm (AI generated speech from Google Research) is going to give Elevenlabs a run for it's money: The text-to-speech project specializes in dialogue between multiple parties, and is available on Github:

Open-source project Soundstorm (AI generated speech from Google Research) is going to give Elevenlabs a run for it's money: The text-to-speech project specializes in dialogue between multiple parties, and is available on Github:

AI Breakfast

326,478 次观看 • 3 年前

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

HOLY FUCK! Zyphra just dropped Zonos - Apache 2.0 licensed, Multilingual, Text to Speech model with INSTANT voice cloning! 🔥 > Zero-shot TTS with Voice Cloning: Input text and a 10-30 second speaker sample to generate high-quality text-to-speech output > Audio Prefix Inputs: Enhance speaker matching by adding an audio prefix to the text, enabling behaviors like whispering that are hard to achieve with voice cloning alone > Multilingual Support: Supports English, Japanese, Chinese, French, and German > Audio Quality & Emotion Control: Fine-tune speaking rate, pitch, frequency, audio quality, and emotions (e.g., happiness, anger, sadness, fear) > Fast Performance: Runs at ~2x real-time speed on an RTX 4090 > Available on the Hugging Face Hub 🤗

Vaibhav (VB) Srivastav

298,858 次观看 • 1 年前

Mundo AI (Mundo AI (YC W25)) is building the world’s largest and highest-quality multilingual data library to help AI labs un-bottleneck their multilingual model development. Congrats on the launch Jason Liao, Naijide, @garrethleee & Kenneth!

Mundo AI (Mundo AI (YC W25)) is building the world’s largest and highest-quality multilingual data library to help AI labs un-bottleneck their multilingual model development. Congrats on the launch Jason Liao, Naijide, @garrethleee & Kenneth!

Y Combinator

49,972 次观看 • 1 年前

The ElevenLabs Reader App is now on Android. Choose from hundreds of high quality AI voices to narrate any article, PDF, or ePub on the go. Download here: It's only available in the US, UK, and Canada today. The app will launch worldwide in the next few weeks once we add support for narration in 32 languages.

The ElevenLabs Reader App is now on Android. Choose from hundreds of high quality AI voices to narrate any article, PDF, or ePub on the go. Download here: It's only available in the US, UK, and Canada today. The app will launch worldwide in the next few weeks once we add support for narration in 32 languages.

ElevenLabs

58,350 次观看 • 2 年前

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Mira Murati says the next AI interface is not a chatbot. It is a model that can listen, see, interrupt, and respond in real time. "The models that we work with today, they're very turn-based." "You talk, they talk, then they go off and think." "While they're thinking, it's almost like they're deaf and blind. They cannot perceive anything else about what's going on." Her new frame: interaction models. "They're not turn-based. They're more like time-based interaction." "They're continuously taking in audio, text, video, and continuously providing output." "We cut this up in chunks of 20 milliseconds... this enables you to catch things like interruptions and simultaneous speech." That is the product shift: from AI as a prompt box to AI as a high-bandwidth collaborator.

Karl Mehta

191,479 次观看 • 1 个月前

Sora isn't available yet to all. But this tool has been trying to take the spotlight with high quality video output. This is Haiper AI. 10 examples:

Sora isn't available yet to all. But this tool has been trying to take the spotlight with high quality video output. This is Haiper AI. 10 examples:

Min Choi

204,114 次观看 • 2 年前

AI is everywhere, but the ROI isn’t. To avoid “workslop,” leaders need to set quality standards—not just mandates. Read the full article here:

AI is everywhere, but the ROI isn’t. To avoid “workslop,” leaders need to set quality standards—not just mandates. Read the full article here:

Harvard Business Review

11,698 次观看 • 9 个月前

Art AI agent 🎨 Certain AI agents, like the Pump Fun AI agent, require generating high-quality images, shaped through prompts that consider lighting, composition and artistic style to achieve optimal realistic results. ZODs currently uses the best text-to-image AI model - Recraft V3. It's somewhat slower than others, but the generated images are incomparably better quality. One step closer to MVP release.

Art AI agent 🎨 Certain AI agents, like the Pump Fun AI agent, require generating high-quality images, shaped through prompts that consider lighting, composition and artistic style to achieve optimal realistic results. ZODs currently uses the best text-to-image AI model - Recraft V3. It's somewhat slower than others, but the generated images are incomparably better quality. One step closer to MVP release.

ZODs

19,378 次观看 • 1 年前

Eleven Music is live. The highest quality AI music model. Another mega push across the ElevenLabs team to produce this very special product. Have a listen!

Eleven Music is live. The highest quality AI music model. Another mega push across the ElevenLabs team to produce this very special product. Have a listen!

Nev Flynn

15,362 次观看 • 1 年前

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation.

DailyPapers

41,699 次观看 • 2 个月前

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

Did xAI just mass-murder the entire voice AI industry? 🤯 Grok just launched two voice APIs. Speech-to-Text and Text-to-Speech. Built on the same stack powering Tesla cars and Starlink support. And priced at 10x cheaper than ElevenLabs. Speech-to-Text: $0.10/hr batch. $0.20/hr streaming. Text-to-Speech: $4.20 per million characters. 25+ languages. Real-time streaming. Speaker diarization. Already outperforming ElevenLabs, Deepgram, and AssemblyAI on word error rate. TTS ships with expressive tags like [laugh], [sigh], , . Voices that don't sound like robots reading a script. ElevenLabs spent years building a voice AI company. xAI built voice AI for cars and satellites.

Vaibhav Sisinty

24,532,279 次观看 • 3 个月前

Got a pair of the Ray-Ban Meta glasses as a birthday gift and, slowly I'm starting to like them. The photo and video quality is not bad (not at iPhone level yet), you can stream Spotify, take calls, and just point them at something and ask Meta AI what it is or to translate text. The trickiest part so far is getting the framing right so shots aren't cut off or off-centre, and you need to avoid moving your head too fast or it affects the quality. They also go dark in bright sun and stay see-through indoors or at night, which I love since you can actually wear them inside too. In restaurants for example. Below are some shots I took in the Bahamas and Mexico. (and to add, I have no affiliation with the brand and this is simply me sharing my experience:))

Tim

32,933 次观看 • 4 个月前

This is wild. Luma AI just dropped Dream Machine that generates AI video from text and image. Unlike Sora, it's open to public today. The quality is insane. 1. Kaku Drop 架空飴

This is wild. Luma AI just dropped Dream Machine that generates AI video from text and image. Unlike Sora, it's open to public today. The quality is insane. 1. Kaku Drop 架空飴

Min Choi

757,534 次观看 • 2 年前

The reason "boss babes" constantly whine about not being able to find any "good men" is because REAL high-quality men avoid them like the plague. They've got options 💯

The reason "boss babes" constantly whine about not being able to find any "good men" is because REAL high-quality men avoid them like the plague. They've got options 💯

Jedediah Bila

11,870 次观看 • 8 个月前

i found a way to make AI videos that don't sound like AI... example below.... sora 2, veo 3.1, kling 2.6 are decent but they all have that robotic AI accent that everyone can detect immediately and when people try replacing the voices with elevenlabs, it always sounds way too professional like it's recorded on a professional mic in a studio but if i'm making a UGC video of someone in their room, i don't want studio quality it should sound like it's actually in that room the workflow i use completely removes that fake AI voice sound why this matters: when your AI voices sound too polished or robotic, people notice. their guard goes up. they disengage. but when your voices sound like they're coming from a real person in a real room, that's when they work the best i created a guide breaking down exactly how: > to create voiceovers that sound completely real > to replace fake-sounding voices in AI videos (not elevenlabs) > to make voices sound like they're in the actual environment, not a studio RT + reply "VOICE" and i'll send you the FULL guide (must follow so i can DM)

i found a way to make AI videos that don't sound like AI... example below.... sora 2, veo 3.1, kling 2.6 are decent but they all have that robotic AI accent that everyone can detect immediately and when people try replacing the voices with elevenlabs, it always sounds way too professional like it's recorded on a professional mic in a studio but if i'm making a UGC video of someone in their room, i don't want studio quality it should sound like it's actually in that room the workflow i use completely removes that fake AI voice sound why this matters: when your AI voices sound too polished or robotic, people notice. their guard goes up. they disengage. but when your voices sound like they're coming from a real person in a real room, that's when they work the best i created a guide breaking down exactly how: > to create voiceovers that sound completely real > to replace fake-sounding voices in AI videos (not elevenlabs) > to make voices sound like they're in the actual environment, not a studio RT + reply "VOICE" and i'll send you the FULL guide (must follow so i can DM)

Miko

247,174 次观看 • 6 个月前