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。

MOSS-TTS Local Transformer v1.5 is here. Clone any voice. Speak any language. Hear every detail. 30+ languages, 48 kHz clarity.

MOSI

1,099 subscribers

121,828 次观看 • 28 天前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

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

292,515 次观看 • 2 年前

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

66,460 次观看 • 2 年前

🎙️ Chatterbox is now available on Comfy Cloud! Zero-shot voice cloning, 23 languages, and expressive TTS — all ready to use with no setup. Clone any voice from just 5 seconds of audio. No training required.

🎙️ Chatterbox is now available on Comfy Cloud! Zero-shot voice cloning, 23 languages, and expressive TTS — all ready to use with no setup. Clone any voice from just 5 seconds of audio. No training required.

ComfyUI

21,722 次观看 • 5 个月前

you can hear every detail in her voice here... the control is insane

you can hear every detail in her voice here... the control is insane

ariana feeds

145,467 次观看 • 1 个月前

Wanted to share something our team has been working on. It's called AI Personas: - create a video clone with just 15 seconds of footage - works w any video, even with gestures or movement, without training - type in 30+ languages and speak w your own voice what do you think?

Wanted to share something our team has been working on. It's called AI Personas: - create a video clone with just 15 seconds of footage - works w any video, even with gestures or movement, without training - type in 30+ languages and speak w your own voice what do you think?

Eric Lu

14,753 次观看 • 1 年前

This is not being talked about enough Zonos is a new open-source voice AI model that clones any voice in under 10 seconds. Here is how I made a voice clone of Matt Wolfe !

This is not being talked about enough Zonos is a new open-source voice AI model that clones any voice in under 10 seconds. Here is how I made a voice clone of Matt Wolfe !

Miguel | AP

85,318 次观看 • 1 年前

"It's ridiculous that we here in the UK present ourselves as this global nation, but we can't speak any languages..." Polyglot Henry Bonsu thinks that more Brits should take the plunge and learn a foreign language. Dawn Neesom | #JeremyVine

"It's ridiculous that we here in the UK present ourselves as this global nation, but we can't speak any languages..." Polyglot Henry Bonsu thinks that more Brits should take the plunge and learn a foreign language. Dawn Neesom | #JeremyVine

Jeremy Vine & Daytime on 5

34,650 次观看 • 6 个月前

MOSS-TTS v1.5 is here, an upgrade to v1.0 from @OpenMOSS. (demo👇)🤖 Key improvements: ⏸️ Inline pause control: [pause 3.2s] now supported mid-sentence 🌍 31 languages, up from 20 — now includes Cantonese, Hindi, Thai, Vietnamese, Tagalog, Swahili and more 🎙️ More stable voice cloning with reduced variance across repeated generations 📝 Better long-reference, short-text cloning All v1.0 capabilities preserved: zero-shot cloning, long-form speech, Pinyin/IPA control, code-switching. 💻

MOSS-TTS v1.5 is here, an upgrade to v1.0 from @OpenMOSS. (demo👇)🤖 Key improvements: ⏸️ Inline pause control: [pause 3.2s] now supported mid-sentence 🌍 31 languages, up from 20 — now includes Cantonese, Hindi, Thai, Vietnamese, Tagalog, Swahili and more 🎙️ More stable voice cloning with reduced variance across repeated generations 📝 Better long-reference, short-text cloning All v1.0 capabilities preserved: zero-shot cloning, long-form speech, Pinyin/IPA control, code-switching. 💻

ModelScope

13,855 次观看 • 1 个月前

Cean speaks in 4 languages already 🤣🤣 AVOCEAN DIVING X TDEX #AVOCEANxTGDO2026 #AVOCEAN 🗣: Did Papa send you to language school? Can you speak any yet? 🐶: Papa didn't send me therrre~ 🗣: Come on, let Grandma hear you speak some. 🐶: Hello~! 🗣️: Hello? Can you speak Japanese? 🐶: Konnichiwa! 🗣️: Can you speak Chinese? 🐶: Ni Hao! 🗣️: Wow so smart! You can speak 3 languages already. Your Papa will be crying now. 🐶: Annyeonghaseyo! 🗣️: Wow, Korean too?

Cean speaks in 4 languages already 🤣🤣 AVOCEAN DIVING X TDEX #AVOCEANxTGDO2026 #AVOCEAN 🗣: Did Papa send you to language school? Can you speak any yet? 🐶: Papa didn't send me therrre~ 🗣: Come on, let Grandma hear you speak some. 🐶: Hello~! 🗣️: Hello? Can you speak Japanese? 🐶: Konnichiwa! 🗣️: Can you speak Chinese? 🐶: Ni Hao! 🗣️: Wow so smart! You can speak 3 languages already. Your Papa will be crying now. 🐶: Annyeonghaseyo! 🗣️: Wow, Korean too?

Mhokstache ✨

79,928 次观看 • 2 个月前

Every chatbot is about to get a voice. ElevenLabs Speech Engine just lets you add human-like voice to any LLM agent in 70+ languages. OpenAI, Claude, Gemini, custom stack. One Prompt. No rebuild needed.🧵 #ad #ElevenAPIPartner

Every chatbot is about to get a voice. ElevenLabs Speech Engine just lets you add human-like voice to any LLM agent in 70+ languages. OpenAI, Claude, Gemini, custom stack. One Prompt. No rebuild needed.🧵 #ad #ElevenAPIPartner

Min Choi

28,220 次观看 • 1 个月前

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

🚀 VoxCPM 2 is live! 🎉 Another open-source AI #TTS model from China — and one that stands shoulder to shoulder with Qwen3-TTS, while bringing everything into a single unified model. After rapid iterations from V1 (zero-shot cloning) to V1.5 (long-form + fine-tuning), #VoxCPM has consistently pushed quality and usability forward. Now, VoxCPM 2 takes it further: 🔹30+ languages — truly global, truly local. 🔹Infinite voice design — type it, hear it, control it. From a whisper to a booming cinematic voice. 🔹Studio-grade audio — 48kHz ultra-high fidelity with emotional depth 🔹Diffusion-Autoregressive cloning — preserves more acoustic and emotional detail than token-based models like Qwen3-TTS 💡 Big shoutout to Grok — used your multi-image video magic for our launch demo. It’s scarily good at keeping visuals consistent across shots. Elon Elon Musk, this one’s for you. 😉 Check the demo & start cloning your dream voice: 🌐 Hugging Face Space: 🤗 Hugging Face Model: 🤖 ModelScope Model: 💻 GitHub： #TTS #AI #VoiceCloning #GrokImagine #ElonMusk #OpenBMB #VoxCPM

OpenBMB

557,835 次观看 • 3 个月前

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.

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

153,890 次观看 • 1 年前

I’m Italian 🇮🇹 Yes, my English is broken. Yes, I have an accent. And somehow… that became my branding. Your accent is not a flaw. It’s proof you learned something new, that you’re brave enough to speak anyway. Languages aren’t meant to sound perfect, they’re meant to connect 💙 Never be scared to use your voice, in any language.

I’m Italian 🇮🇹 Yes, my English is broken. Yes, I have an accent. And somehow… that became my branding. Your accent is not a flaw. It’s proof you learned something new, that you’re brave enough to speak anyway. Languages aren’t meant to sound perfect, they’re meant to connect 💙 Never be scared to use your voice, in any language.

𝐃𝐞𝐥𝐢𝑅𝑖𝑛 🪢🩷

29,005 次观看 • 4 个月前

Every year (around March/April and October) the City is treated to the spectacular views of the Tabebuia Rosea a.k.a Cherry Blossom/Pink Poui. Anyone knows what this tree is called in any of our local languages? #ForABetterCity

Every year (around March/April and October) the City is treated to the spectacular views of the Tabebuia Rosea a.k.a Cherry Blossom/Pink Poui. Anyone knows what this tree is called in any of our local languages? #ForABetterCity

Kampala Capital City Authority (KCCA)

31,908 次观看 • 1 年前

If somebody working in other states don’t want to speak that states official local language then why go there to make living or do business? Get out and go back to your home state. (Listening to below attach clip will further make more sense) 1. Though normally don’t agree with politicians like Tejasvi Surya or for that matter Raj Thackeray style of divisive politics based on language. But here what wrong had #TejasSurya said? He had not incited people for violence or to hate others. He just said migrants people who had come to Karnataka for a living should speak in local language. What wrong in that ? 2. This is not just a question of people speaking Kannada or Tulu or Marathi,Tamil,Malayalam,Telugu or Bengali and other languages. If somebody is going in other states in our country for job or doing business then they should not only respect local people’s culture and languages butthey must also learn and speak that local language. Else people should go to any states in India as tourist and return back to their home state. 3. Why local people in Karnataka,Maharashtra,TamilNadu, West Bengal or any states are upset and angry not because of outsiders migrations but migrant people refusing to learn and speak local language and migrants behave very arrogantly many times, sometimes violently against local people. Even PM #NarendraModi had suggested people to learn 2-3 other states languages apart from our own mother tongue language. 4. Any govt organisation sending people to other states must ensure that their employees learn local language before giving them job profile training or after transfer to other states . Any private sector Businesses wanting to setup industries or offices in any states, must ensure they learn local language of that particular state, employ local people and when they are hiring people from other states then migrant employees are made to learn and speak local languages. If not then better leave that state. 5. 28 States in Bharat ie. India were formed on linguistic ie. Language basis. How can we afford to become one nation with only one language,with one culture, one system which is what people call it #Woke #Wokisme culture? Our SanatanDharma is very vast diverse ocean of many languages,rituals,food habits,different ways of life. We must maintain that diversity as we are not ChineseCommunistsParty ruled one party one Communists-Maoists country. 6. Hearing that few Business people saying they will shift their businesses from #Bengaluru to Pune or some other place as they and their employees are pissed off by local population insistence of speaking in local language and that they don’t want to learn and speak in local language. Why are you there first of all? You have not gone there as tourists for few days but you people found some business/employment opportunities to make a living then better learn and speak local language or go back to your home states. 7. People learn English before going to USA,UK,Australia and other English speaking countries. People learn French,Spanish,Mandarine,Japanese,Arabic languages before or after going to those countries . Else how can they survive and continue to work in these countries? Then why people in our country unwilling and refuse to learn and speak local languages of states where they work and make a living ? 8. Of course we the people of Bharat ie. India are united but without respecting,learning other states languages and instead rather becoming arrogant-violent, how can we preserve,promote and protect our so many wonderful-beautiful languages and such an ancient diverse culture ? 👇

KailashGWagh 🇮🇳

28,066 次观看 • 1 年前

Podcasters - what if I told you could offer your pod to any listener around the world, in their own local language but still keep it in your own voice? That’s the pilot we’re launching Spotify! It’s called Voice Translation and using AI, translates podcasts episodes into alternate languages, all in the podcaster’s voice. It’s pretty insane. Take a look and let me know what you think!

Podcasters - what if I told you could offer your pod to any listener around the world, in their own local language but still keep it in your own voice? That’s the pilot we’re launching Spotify! It’s called Voice Translation and using AI, translates podcasts episodes into alternate languages, all in the podcaster’s voice. It’s pretty insane. Take a look and let me know what you think!

Daniel Ek

3,174,221 次观看 • 2 年前

This is INSANE. Google just dropped a free AI voice dictation app for iOS and Mac. Every premium feature works without any subscription. 100% free, runs fully local, powered by Gemma 4.

This is INSANE. Google just dropped a free AI voice dictation app for iOS and Mac. Every premium feature works without any subscription. 100% free, runs fully local, powered by Gemma 4.

Shubham Saboo

365,843 次观看 • 1 个月前

🚀 Meet the new Qwen3-TTS lineup: VoiceDesign & VoiceClone! Create, control, and clone voices—faster and more expressive than ever. ⚡ VoiceDesign-VD-Flash • Fully controllable speech via free-form text instructions — tone, rhythm, emotion, persona • No preset voices. Design your own unique vocal identity • Outperforms GPT-4o-mini-tts & Gemini-2.5-pro on role-play benchmarks ⚡ VoiceClone-VC-Flash • Clone any voice from just 3 seconds of audio • Generate speech in 10 languages (CN / EN / JP / ES + more) • 15% lower WER vs. ElevenLabs & GPT-4o-Audio in multilingual tests • Context-aware cadence for more natural delivery 🎙️ Try it now • Qwen Chat: • Blog:

🚀 Meet the new Qwen3-TTS lineup: VoiceDesign & VoiceClone! Create, control, and clone voices—faster and more expressive than ever. ⚡ VoiceDesign-VD-Flash • Fully controllable speech via free-form text instructions — tone, rhythm, emotion, persona • No preset voices. Design your own unique vocal identity • Outperforms GPT-4o-mini-tts & Gemini-2.5-pro on role-play benchmarks ⚡ VoiceClone-VC-Flash • Clone any voice from just 3 seconds of audio • Generate speech in 10 languages (CN / EN / JP / ES + more) • 15% lower WER vs. ElevenLabs & GPT-4o-Audio in multilingual tests • Context-aware cadence for more natural delivery 🎙️ Try it now • Qwen Chat: • Blog:

Qwen

180,928 次观看 • 6 个月前