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。

Introducing OpenVoice 🔊 Instant voice cloning that requires only a short audio clip to replicate voice and generate speech in multiple languages and tones Listen to the examples They are able to replicate voices with only one sentence Demo to try below:

Allen T.

28,038 subscribers

32,935 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Everett World 的头像

Everett World2 年前

I'm so interested in progress of this tech - with elevnlabs and stuff like that, we're getting really close to applications like realistic dubbing. But number 1 for me would be AI talking like a human and sounding like a human - GPT Voice is amazing and it feels like we're not that far away.

Allen T. 的头像

Allen T.2 年前

I completely agree - we are really close. You can still hear the slight robotic voice intertwined with the replicated voice. I wonder if the general public that isn’t well versed in AI would pick up the difference

Min Choi 的头像

Min Choi2 年前

This is getting pretty good. 2024 is going to be wild 🔥

Allen T. 的头像

Allen T.2 年前

It’s going to be an insane year lol I honestly can’t even predict where we’ll be by Jan 2025

Halim Alrasihi 的头像

Halim Alrasihi2 年前

The voice style feature is so nice, I was missing that on other text2voice tools

Allen T. 的头像

Allen T.2 年前

100% agree. I am going to experiment with my own voice and see if the generated style change matches my own real style change

Ruben Hassid 的头像

Ruben Hassid2 年前

Can it make me sound like Morgan Freeman or do I have to stick to my regular voice?

Allen T. 的头像

Allen T.2 年前

If you have an audio clip of Morgan Freeman to use as a reference then you should be able to replicate the voice. The video demo they use Elon’s voice

S!R Charles 的头像

S!R Charles2 年前

Did you make it work? I tried and got different error messages every time.. syntax error etc..

Allen T. 的头像

Allen T.2 年前

Very weird. It was working well when I was experimenting with it earlier this morning. I was using the reference audios that were provided though and not my own voice yet

相关视频

MIT CSAIL and MyShell.AI researchers introduce OpenVoice V2, a text-to-speech model that can clone any voice and speak in many languages. Imagine your voice going global in multiple languages. OpenVoice V2 breaks the language barrier and redefines voice interactions.

MIT CSAIL and MyShell.AI researchers introduce OpenVoice V2, a text-to-speech model that can clone any voice and speak in many languages. Imagine your voice going global in multiple languages. OpenVoice V2 breaks the language barrier and redefines voice interactions.

MIT CSAIL

66,603 次观看 • 2 年前

Introduce OpenVoice V2 - a Text-to-Speech model that can clone any voice and speak in any language. Developed by MyShell and MIT CSAIL researchers. 🌐 Imagine your voice going global in multiple languages. 🔊 OpenVoice V2 breaks the language barrier and redefines voice interaction.

Introduce OpenVoice V2 - a Text-to-Speech model that can clone any voice and speak in any language. Developed by MyShell and MIT CSAIL researchers. 🌐 Imagine your voice going global in multiple languages. 🔊 OpenVoice V2 breaks the language barrier and redefines voice interaction.

MyShell.AI

292,600 次观看 • 2 年前

Introducing Voice Cloning on Hedra! Record a quick clip, and we’ll clone your voice to bring your Hedra characters to life. Just upload or generate an image, and let your character speak in your voice. Try it for yourself! (Available to paid users only)

Introducing Voice Cloning on Hedra! Record a quick clip, and we’ll clone your voice to bring your Hedra characters to life. Just upload or generate an image, and let your character speak in your voice. Try it for yourself! (Available to paid users only)

Hedra

39,119 次观看 • 1 年前

Instant Voice Cloning 3 seconds of audio is all you need. Text-to-voice AI generated voices with <1 second latency. 🧵 A thread

Instant Voice Cloning 3 seconds of audio is all you need. Text-to-voice AI generated voices with <1 second latency. 🧵 A thread

Linus ✦ Ekenstam

576,641 次观看 • 3 年前

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Introducing Lightning V3 - it beats every model we tested against. ElevenLabs, Cartesia, OpenAI. Lightning sets a new SOTA with V3 in conversational text-to-speech. → Highest MOS score for conversational TTS at 3.9 → ~76% win rate vs gpt-4o-mini-tts on naturalness → 15 languages with mid-sentence code-switching → Built from scratch for voice agents, not read-aloud Every TTS model sounds clean in a demo. You type a sentence and you get beautiful audio. Voice agents don't work that way. They stream. They're generating audio in real-time chunks with half the context missing. That's where everything breaks. A great reading voice and a great conversational voice are fundamentally different things. A conversational voice has to sound like it's thinking - with the pauses, the rhythm shifts, the reactions. It has to handle the way real people actually talk, including switching languages mid-sentence. That's what V3 does. V3.1 also ships voice cloning. 5 to 15 seconds of audio, no fine-tuning, production-grade clone across 15 languages. Blog link in the comments.

Sudarshan Kamath

71,298 次观看 • 6 个月前

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

299,066 次观看 • 1 年前

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️

Introducing Dialog 1.0 - Ultra-emotional AI Text-To-Speech model Outperforms Elevenlabs on expressiveness and quality 3 to 1 <1% error rate Supports 30+ languages Best in class voice cloning Low latency: 303ms TTFA (Time to First Audio) Experience it for yourself on Read more below⬇️

PlayAI

196,182 次观看 • 1 年前

Introducing ElevenLabs GPT, my latest custom GPT that brings any prompt to life with a realistic voice! 🗣️ You can: - generate an audiobook with one prompt! - have online articles read to you - listen to any docs you upload Watch the demo below to see it in action! 🚀

Introducing ElevenLabs GPT, my latest custom GPT that brings any prompt to life with a realistic voice! 🗣️ You can: - generate an audiobook with one prompt! - have online articles read to you - listen to any docs you upload Watch the demo below to see it in action! 🚀

Ammaar Reshi

232,061 次观看 • 2 年前

Introducing Multilingual Voices We partnered with Baklavastory, our neighbor in the Mission, to show what it sounds like when a business's character and warmth stay consistent, no matter who calls or what language they speak. It's easy to translate speech, but much harder to preserve a single identity across languages. Every language has different rhythms, tones, and emphasis. When you change the language, identity tends to get lost in that shift, and your voice ends up sounding like someone else. With Multilingual Voices, pick a voice and keep one brand identity in every market you serve:

Karan Goel

5,398,650 次观看 • 10 天前

The Biggest Scandal in Alzheimer’s Research “$300 million went towards funding something that never existed. They were never able to replicate these studies, and labs all over the world were getting funded to replicate this amyloid beta 56, and no one was able to replicate it over a 20 year period." Louisa Nicola

The Biggest Scandal in Alzheimer’s Research “$300 million went towards funding something that never existed. They were never able to replicate these studies, and labs all over the world were getting funded to replicate this amyloid beta 56, and no one was able to replicate it over a 20 year period." Louisa Nicola

Shawn Ryan

98,702 次观看 • 4 个月前

Audio8-TTS-0.1B is a tiny text to speech model for zero-shot voice cloning. It supports multiple languages and can easily fit on consumer devices.

Audio8-TTS-0.1B is a tiny text to speech model for zero-shot voice cloning. It supports multiple languages and can easily fit on consumer devices.

AI Search

16,899 次观看 • 1 个月前

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.

Real-time AI conversations are here! PlayHT, one of the best text-to-speech models I’ve used, now has a latency of less than 300ms. Checkout how fast it outputs audio 🤯 Also, my experience cloning my own voice and links to try it for free are below.

Alvaro Cintas

335,391 次观看 • 2 年前

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

New native audio capabilities in Gemini 2.5 enable text-to-speech in over 24 languages. 🔊Voices are more natural and expressive, and you can seamlessly switch between languages.

Google

155,500 次观看 • 1 年前

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

Speech to Speech is now available in 29 languages. In November, we launched Speech to Speech, enabling you to transform your voice into another character with full control over emotions, timing, and delivery. Today we're making Speech to Speech multilingual. Use Speech to Speech to get more control than with prompting alone. Simply say it how you want it, choose a target voice, and generate.

ElevenLabs

113,343 次观看 • 2 年前

We’re finally breaking the silence 🔊 Meet Higgsfield Audio, our all-in-one AI audio generator. Higgsfield is now the ultimate full-cycle AI content production platform. 🧩 Give a voice to any of your text with 21 voice presets 🧩 Change the voice in any of your videos 🧩 Translate and lip-sync any speech in 10 built-in languages An end-to-end AI workflow under one subscription.

We’re finally breaking the silence 🔊 Meet Higgsfield Audio, our all-in-one AI audio generator. Higgsfield is now the ultimate full-cycle AI content production platform. 🧩 Give a voice to any of your text with 21 voice presets 🧩 Change the voice in any of your videos 🧩 Translate and lip-sync any speech in 10 built-in languages An end-to-end AI workflow under one subscription.

Higgsfield AI 🧩

89,429 次观看 • 6 个月前

Samkeliso dazzled his fans with his dances. He is the only one able to accurately replicate his famous dance moves.

Samkeliso dazzled his fans with his dances. He is the only one able to accurately replicate his famous dance moves.

PSAFLIVE

535,867 次观看 • 5 个月前