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。

Something fun with voice using generative AI! Here’re four audio clips of either my voice clone (3 clips) or me (1 clip) telling AI jokes. Can you tell which is the real me? Please reply below! Thanks Speechlab, Inc. (an AI Fund portfolio company) for building the voice clone.

Andrew Ng

1,771,793 subscribers

718,184 次观看 • 2 年前 •via X (Twitter)

喜剧科学技术

Anya Rossi• Live Now

Private livecam show

10 条评论

BeyondBacktesting 的头像

BeyondBacktesting2 年前

@Speechlab_ai @AI_Fund 1. AI 2. AI 3. Human 4. AI

Márcio Oliveira 的头像

Márcio Oliveira2 年前

@Speechlab_ai @AI_Fund Really impressive work! I believe joke #4 is you.

Roman Pshichenko 的头像

Roman Pshichenko2 年前

@Speechlab_ai @AI_Fund I say 4 because the pause between algo rhythms was to big of a part of the joke.

Abhishek Singh 的头像

Abhishek Singh2 年前

@Speechlab_ai @AI_Fund 1-2-3 are AI and 4 is the real Andrew because there's a pause in algo-rhythms while in other cases a hyphen is not resulting in a pause

Ram Ahluwalia CFA, Lumida 的头像

Ram Ahluwalia CFA, Lumida2 年前

@Speechlab_ai @AI_Fund 3 is real

Amit 的头像

Amit2 年前

@Speechlab_ai @AI_Fund all AI.

carlos keeps learning 的头像

carlos keeps learning2 年前

@Speechlab_ai @AI_Fund 4 is real

John Berryman 的头像

John Berryman2 年前

@Speechlab_ai @AI_Fund the ambient noise in 1,2, and 3 are the same. 4 has different ambient noise. But other than that tell, I don't think I would have known!

Rohan Sharma 的头像

Rohan Sharma2 年前

@Speechlab_ai @AI_Fund While all four clips are remarkably similar, the subtle nuances and distinctive qualities of your authentic voice may still set it apart. Kudos to @Speechlab_ai and @AI_Fund for pushing the boundaries of AI technology!

Sai 的头像

Sai2 年前

@Speechlab_ai @AI_Fund 3 is real because there was a slight mismatch in the titled text and the spoken. Having said that, it’s damn hard to tell otherwise!

相关视频

Have a conversation with yourself in real-time. With Hedra’s Live Avatars, you can create a real-time AI clone in 3 steps: 1. Upload a photo 2. Clone your voice 3. Start talking (to you) Watch me chat with my AI twin in real time. Try it for yourself in Hedra!

Have a conversation with yourself in real-time. With Hedra’s Live Avatars, you can create a real-time AI clone in 3 steps: 1. Upload a photo 2. Clone your voice 3. Start talking (to you) Watch me chat with my AI twin in real time. Try it for yourself in Hedra!

Hedra

1,518,823 次观看 • 1 年前

You really, really should not trust audio clips anymore Even a couple months ago, it used to take a commercial service to clone a voice. No more. Here is me creating a voice clone of myself using just a 10 second reference clip on my home computer This is all real time, no cuts

You really, really should not trust audio clips anymore Even a couple months ago, it used to take a commercial service to clone a voice. No more. Here is me creating a voice clone of myself using just a 10 second reference clip on my home computer This is all real time, no cuts

Ethan Mollick

606,383 次观看 • 1 年前

Michael Caine has signed a deal with AI company ElevenLabs to make a clone of his voice. The company will have the voice available on a marketplace where users can request access to the voice to create content.

Michael Caine has signed a deal with AI company ElevenLabs to make a clone of his voice. The company will have the voice available on a marketplace where users can request access to the voice to create content.

DiscussingFilm

1,281,299 次观看 • 9 个月前

AI voice clones have hit the White House AGAIN, now impersonating the Secretary of State to other Gov officials to try to steal secrets/access. Here is a video of me live demoing how quick and easy it is to clone a voice to hack and how to catch AI voice clone attacks in action!

AI voice clones have hit the White House AGAIN, now impersonating the Secretary of State to other Gov officials to try to steal secrets/access. Here is a video of me live demoing how quick and easy it is to clone a voice to hack and how to catch AI voice clone attacks in action!

Rachel Tobac

52,456 次观看 • 1 年前

The voice AI company that raised $100M from companies like NVIDIA just dropped Sonic-3. • it has latency 190ms first byte (fastest in production) • can laugh, show sadness & happiness • has 42 languages in one voice • handles acronyms, dates, phone numbers correctly • can clone anyone’s voice • you can adjust the speed & volume in real time.

The voice AI company that raised $100M from companies like NVIDIA just dropped Sonic-3. • it has latency 190ms first byte (fastest in production) • can laugh, show sadness & happiness • has 42 languages in one voice • handles acronyms, dates, phone numbers correctly • can clone anyone’s voice • you can adjust the speed & volume in real time.

Alvaro Cintas

28,103 次观看 • 10 个月前

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇

Building real-time voice AI just got a lot easier 🤖✨ Introducing our new Python AI SDK for building real-time AI integrations directly into Stream Video. With out-of-the-box integrations with , Deepgram, , OpenAI, Moonshine AI, and more, developers can mix and match between real-time Voice AI, TTS or STT models. Get started 👇

Stream

224,788 次观看 • 1 年前

people always ask me how they can create long, consistent AI videos with audio. well creatify aurora solves a big part of that and there are some new models coming soon too for more action + audio. I created his voice with dia tts which i think great at capturing emotional speeches. then I cloned his voice using minimax voice clone and use it on minimax tts 2.6. here is the my full conversation with claude for images and text to speech inputs:

people always ask me how they can create long, consistent AI videos with audio. well creatify aurora solves a big part of that and there are some new models coming soon too for more action + audio. I created his voice with dia tts which i think great at capturing emotional speeches. then I cloned his voice using minimax voice clone and use it on minimax tts 2.6. here is the my full conversation with claude for images and text to speech inputs:

gokaygokay

38,341 次观看 • 8 个月前

One of these voice clones *actually* sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.

One of these voice clones actually sounds like the original. That’s because Mirage audio generates more expressive output than other models on the market. Our research team built Mirage audio to create more realistic voices. Launching today, this new model solves 3 common challenges in AI audio: 1. It preserves the original speaker’s accent 2. The performance feels dynamic, not flat 3. Delivery matches how people really speak Thanks to our frontier AI research, our voice clone feature preserves the little details that make your voice unique. So your voice actually sounds like you.

Mirage

14,914 次观看 • 8 个月前

AI can clone almost anyone’s voice. Scammers can use a cloned voice to fool almost anyone. The tech is so advanced, it’s even fooled James Nesbitt! In support of the Home Office’s ‘Stop! Think Fraud’ campaign, we’re on a mission to help you stay safe from voice cloning. 1/2

AI can clone almost anyone’s voice. Scammers can use a cloned voice to fool almost anyone. The tech is so advanced, it’s even fooled James Nesbitt! In support of the Home Office’s ‘Stop! Think Fraud’ campaign, we’re on a mission to help you stay safe from voice cloning. 1/2

Starling

35,276 次观看 • 1 年前

You could build a bespoke influencer right now using only AI. Scrape clips or record yourself. Automate the rest: - scrape - LLM audit - bucket by category - process - voice changer This stack already works - the real unlock is realtime. Clips: Emiru, gabimfmoura

You could build a bespoke influencer right now using only AI. Scrape clips or record yourself. Automate the rest: - scrape - LLM audit - bucket by category - process - voice changer This stack already works - the real unlock is realtime. Clips: Emiru, gabimfmoura

A.I.Warper

285,124 次观看 • 7 个月前

And no he doesn't speak English. Yes, it's an AI voice translation of the original French audio, with AI lip-synching to match the new audio, so you can avoid embarrassing yourselves with the dumb "Is this AI?" question.

And no he doesn't speak English. Yes, it's an AI voice translation of the original French audio, with AI lip-synching to match the new audio, so you can avoid embarrassing yourselves with the dumb "Is this AI?" question.

David Hundeyin

305,870 次观看 • 1 年前

Suzanne Somers’ husband says he’s created an AI clone of his late wife, two years after her death. The digital twin was built using her voice, interviews, and personal memories. “When you look at the finished one next to the real Suzanne, you can’t tell the difference.”

Suzanne Somers’ husband says he’s created an AI clone of his late wife, two years after her death. The digital twin was built using her voice, interviews, and personal memories. “When you look at the finished one next to the real Suzanne, you can’t tell the difference.”

Shadow of Ezra

1,885,364 次观看 • 10 个月前

Clone any UGC video with AI in 18 minutes These are the 6 steps to swap the creator in a UGC video and regenerate it with a brand new AI character. 0:00 Intro 0:55 Step 1 - Finding the video to clone 2:11 Step 2 - Generating your new character 4:30 Step 3 - Cutting the original into clips 5:37 Step 4 - Generating clip 1 in Seedance 10:04 Step 5 - Locking the voice across clips 15:38 Step 6 - Editing the final video 17:33 Summary

Mike Futia

10,862 次观看 • 1 个月前

Demonstration of the new Cyn voice model WIP! NOT an AI clone of Cyn. It's my recorded impression put through an 11labs voice changer, then I adjusted pitch and added some subtle robo-ish effect. Happy where this one is at for now

Demonstration of the new Cyn voice model WIP! NOT an AI clone of Cyn. It's my recorded impression put through an 11labs voice changer, then I adjusted pitch and added some subtle robo-ish effect. Happy where this one is at for now

DT

23,277 次观看 • 1 年前

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

I've just tested the EVI 3 speech-to-speech model by Hume Hume AI, and this is the most realistic voice cloning I’ve heard. It doesn’t just clone the sound of your voice — it captures your tone, your speech patterns, your personality. Feels like your voice is thinking in real time. What’s wild is: — It’s not text-to-speech. It’s speech-to-speech. — You speak → it clones your voice + vibe — And it’s compatible with LLMs like Groq, Anthropic, Deepseek - Try talking to a voice clone: - Want more control? Customize it here: This changes how we’ll interact with AI voices. No more robotic replies — these sound human.

Aaliya

28,046 次观看 • 1 年前

Tried more 🎙️ AI voice cloning of my own voice to see if I can make into an audio book with I used a 5 min audio sample from a podcast with only my own voice cut It sounds a bit too American/Canadian for me but 90% close I think

Tried more 🎙️ AI voice cloning of my own voice to see if I can make into an audio book with I used a 5 min audio sample from a podcast with only my own voice cut It sounds a bit too American/Canadian for me but 90% close I think

@levelsio

144,119 次观看 • 2 年前

xAI is cooking 🔥 They just launched Grok Voice, a platform for building AI voice agents. - You can build voice agents in under 2 minutes - No code required - Human-like conversations with sub-second latency - Supports 25+ languages - 80+ built-in voices or clone your own - Works with Gmail, Google Calendar, Outlook, Notion, MCPs, and more - Starts at $0.05/min and includes a free phone number

xAI is cooking 🔥 They just launched Grok Voice, a platform for building AI voice agents. - You can build voice agents in under 2 minutes - No code required - Human-like conversations with sub-second latency - Supports 25+ languages - 80+ built-in voices or clone your own - Works with Gmail, Google Calendar, Outlook, Notion, MCPs, and more - Starts at $0.05/min and includes a free phone number

AshutoshShrivastava

144,824 次观看 • 1 个月前