Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

we’re open sourcing a voice model built for how people actually speak. 20+ languages. native accents. mid-sentence language switching. Expressive yours soon.

rumik_ai's profile picture

rumik

4,001 subscribers

28,466 görüntüleme • 1 ay önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)
0:52

meet silk mulberry 1.5, a voice model built to outperform expectations. - 162ms end-to-end latency - replies before you finish reading the message. - matches elevenlabs v3 on the MOS benchmark while being 95% cheaper. (₹0.40/min vs ₹9.40/min) ⁃ you don't pick a voice, you design one - describe the age, accent, pitch, emotion, whatever you want, only limit is your imagination. - mid-sentence language switching across 20+ languages with native accents, plus expressive range (whispers, singing and much more)

rumik

31,360 görüntüleme • 2 ay önce

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.
1:33

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 görüntüleme • 5 ay önce

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.
0:52

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

153,990 görüntüleme • 1 yıl önce

India is a voice-first nation: countless languages, scripts, and accents. Introducing Indic-Transcribe: built to understand India as she actually speaks. Built by @BodhanAI and @AI4Bharat. 🎙️ 1.2B params · 26 languages + English Live on 05.09.2026
4:49

India is a voice-first nation: countless languages, scripts, and accents. Introducing Indic-Transcribe: built to understand India as she actually speaks. Built by @BodhanAI and @AI4Bharat. 🎙️ 1.2B params · 26 languages + English Live on 05.09.2026

Mitesh Khapra

150,042 görüntüleme • 23 gün önce

Conversational AI now supports Multivoice mode - letting AI agents switch voice and language mid-sentence. English-speaking agents can say Italian words in a native Italian voice or alternate between characters. Useful for language apps and multi-character audio experiences.
2:30

Conversational AI now supports Multivoice mode - letting AI agents switch voice and language mid-sentence. English-speaking agents can say Italian words in a native Italian voice or alternate between characters. Useful for language apps and multi-character audio experiences.

ElevenLabs

28,686 görüntüleme • 1 yıl önce

We're launching Veena TTS 🪕 on June 20 Our flagship text-to-speech model for Indian languages 🇮🇳 Natural, expressive, and actually sounds like us. We’re launching two models: Veena Lite >Open-source and lightweight >4 unique, natural-sounding voices >The first open-source TTS model designed for real creative use cases Veena Max >Available via our web app >15 expressive, high-quality voices >Perfect for storytelling, dubbing, voiceovers, and content creation
0:58

We're launching Veena TTS 🪕 on June 20 Our flagship text-to-speech model for Indian languages 🇮🇳 Natural, expressive, and actually sounds like us. We’re launching two models: Veena Lite >Open-source and lightweight >4 unique, natural-sounding voices >The first open-source TTS model designed for real creative use cases Veena Max >Available via our web app >15 expressive, high-quality voices >Perfect for storytelling, dubbing, voiceovers, and content creation

Dheemanth Reddy

80,431 görüntüleme • 1 yıl önce

Different languages. Different accents. One voice experience built to understand them. At the #HUMAIN booth at #LEAP26, visitors put HUMAIN Voice to the test, recording their own voices, in their own languages and accents, and experiencing how AI can make every interaction feel more natural and human. This is voice AI built for the way the world speaks. #LEAP26 #TheEndOfLimits
1:04

Different languages. Different accents. One voice experience built to understand them. At the #HUMAIN booth at #LEAP26, visitors put HUMAIN Voice to the test, recording their own voices, in their own languages and accents, and experiencing how AI can make every interaction feel more natural and human. This is voice AI built for the way the world speaks. #LEAP26 #TheEndOfLimits

HUMAIN

29,203 görüntüleme • 5 gün önce

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.
1:26

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 görüntüleme • 2 yıl önce

OM1 now includes Multi-Language Support, seamlessly transitioning between languages mid conversation with no additional setup. This means users can speak in their native language and receive responses back either in the same language or in any language of their choice. We've made conversing with robots universal for homes and workplaces, eliminating language barriars.
0:26

OM1 now includes Multi-Language Support, seamlessly transitioning between languages mid conversation with no additional setup. This means users can speak in their native language and receive responses back either in the same language or in any language of their choice. We've made conversing with robots universal for homes and workplaces, eliminating language barriars.

OpenMind

11,796 görüntüleme • 3 ay önce

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.
1:26

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 görüntüleme • 2 yıl önce

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.
0:57

Today, we’re excited to introduce Miso One, the most emotive voice model in the world. Miso One is an 8-billion-parameter text-to-speech model for highly expressive speech generation. It emotes like a human and responds faster than a human, with just 110 milliseconds of latency. We’ve open-sourced the model weights, with API access coming soon. Hear how Miso One sounds in the thread below.

Aoden Teo

5,242,508 görüntüleme • 3 ay önce

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]
0:31

We are launching the Eleven v3 (alpha) API. Built for async use cases, Eleven v3 (alpha) delivers the most expressive Text to Speech model: - Dialogue mode, unlimited amount of speakers - 70+ languages - Enhanced voice and emotional control with [audio tags]

ElevenLabs

8,188,919 görüntüleme • 1 yıl önce

Introducing ✨Tiny Aya✨, a family of massively multilingual small language models built to run where people actually are. Tiny Aya delivers strong multilingual performance in 70+ global languages in a 3.35B parameter model, efficient enough to run locally, even on a phone.
0:30

Introducing ✨Tiny Aya✨, a family of massively multilingual small language models built to run where people actually are. Tiny Aya delivers strong multilingual performance in 70+ global languages in a 3.35B parameter model, efficient enough to run locally, even on a phone.

Cohere Labs

195,183 görüntüleme • 6 ay önce

We’re open sourcing a humanoid robot for under $500. I hated that the coolest technology of our generation was inaccessible to most builders. So we built one. Coming soon. Comment “VIBE” and I’ll send you the Discord.
0:51

We’re open sourcing a humanoid robot for under $500. I hated that the coolest technology of our generation was inaccessible to most builders. So we built one. Coming soon. Comment “VIBE” and I’ll send you the Discord.

Archer Lin

40,391 görüntüleme • 2 ay önce

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:
2:06

Introducing Realtime TTS-2, a new generation of voice model built for realtime conversation. It is the first voice model that hears the conversation, takes natural-language voice direction, holds one voice identity across over 100 languages, and speaks like a person who is paying attention. The result is voice AI that feels as good as it sounds. Try it out: Learn More:

Inworld AI

327,238 görüntüleme • 4 ay önce

Do you dream of a world where some of the top podcasts would be spoken in your native language? Well, that’s now possible. We’re excited to pilot Voice Translation, a groundbreaking feature powered by AI that translates podcasts into additional languages—all in the podcaster’s voice.
0:53

Do you dream of a world where some of the top podcasts would be spoken in your native language? Well, that’s now possible. We’re excited to pilot Voice Translation, a groundbreaking feature powered by AI that translates podcasts into additional languages—all in the podcaster’s voice.

Spotify News

412,117 görüntüleme • 3 yıl önce

This Japanese guy saw these two Nigerian women on the street USA and told them he could speak their native languages…Wait for the mama reaction when she found out he could actually speak Edo language and when he asked mama if she Japa from Nigeria😭😂
1:56

This Japanese guy saw these two Nigerian women on the street USA and told them he could speak their native languages…Wait for the mama reaction when she found out he could actually speak Edo language and when he asked mama if she Japa from Nigeria😭😂

Oyindamola🙄

82,182 görüntüleme • 1 ay önce

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.
0:45

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 görüntüleme • 8 ay önce

❰New customizable model!❱ Get expressive, lively mouth movements without needing VBridger!! We’re offering a 70% discount for the first 10 people who grab one.
0:56

❰New customizable model!❱ Get expressive, lively mouth movements without needing VBridger!! We’re offering a 70% discount for the first 10 people who grab one.

ユウ Yuu🎀

57,079 görüntüleme • 4 ay önce

Meet MiniMax Speech 2.6 — Ultra-Fast, Ultra-Human, Ultra-Smart ⚡Ultra-Fast: <250 ms latency for real-time conversational interactions 💬Smart Text Normalization for URLs, emails, dates, numbers & more 🎙️Full Voice Clone + Fluent LoRA: natural, expressive, effortless 🌍40+ languages with inline code switching Fluent anytime. In every language. 👉 API available:
1:02

Meet MiniMax Speech 2.6 — Ultra-Fast, Ultra-Human, Ultra-Smart ⚡Ultra-Fast: <250 ms latency for real-time conversational interactions 💬Smart Text Normalization for URLs, emails, dates, numbers & more 🎙️Full Voice Clone + Fluent LoRA: natural, expressive, effortless 🌍40+ languages with inline code switching Fluent anytime. In every language. 👉 API available:

Hailuo AI (MiniMax)

553,377 görüntüleme • 10 ay önce