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。

⚡️ JUST DROPPED: Create custom AI voices in seconds! > Mix multiple voices > Zero coding needed > Intuitive & slick UI with voice sliders > Built with Kokoro-82M; blazing fast! [🗣️ SOUND:ON]

Gradio

56,937 subscribers

49,080 次观看 • 1 年前 •via X (Twitter)

教育科学技术

Anya Rossi• Live Now

Private livecam show

5 条评论

Gradio 的头像

Gradio1 年前

🎯 Kokoro Voice Mixer Studio is perfect for: > YouTubers needing unique voiceovers > Developers building voice apps > Content creators > Podcasters > Anyone wanting a custom AI voice! Create your perfect voice:

AssemblyAI 的头像

AssemblyAI1 年前

Announcing: Our most advanced speech-to-text model goes beyond accuracy to capture the real-world complexity of human conversation and deliver reliable, source-of-truth audio data. Explore Universal-2 updates 👇

haareblond 的头像

haareblond1 年前

cool!!! only hting missing is finetuning code xD

Momo 的头像

Momo1 年前

whats the streaming latency?

Michael Dufour (e/acc) 的头像

Michael Dufour (e/acc)1 年前

This seems very cool ! Having a voice sample file input and choosing emotion samples sliders using this UI would allow something never done yet afaik ?

相关视频

Introducing editorcn 📝 by Shadcn Labs > Built on Tiptap > Zero config, one command setup. > shadcn/ui compatible (simply copy-paste) > Rich text, Notion-style editors with 20+ built-in controls > Fully customizable 100% free and open-source.

Introducing editorcn 📝 by Shadcn Labs > Built on Tiptap > Zero config, one command setup. > shadcn/ui compatible (simply copy-paste) > Rich text, Notion-style editors with 20+ built-in controls > Fully customizable 100% free and open-source.

Aniket Pawar

46,524 次观看 • 8 天前

crazy...google gemini can create amazing infographics with just one click. > go to gemini app > type a text prompt with canvas option > click on create infographics and its done finally, an ai can create useful infographics in seconds!

crazy...google gemini can create amazing infographics with just one click. > go to gemini app > type a text prompt with canvas option > click on create infographics and its done finally, an ai can create useful infographics in seconds!

Shubham Saboo

75,621 次观看 • 11 个月前

Vibe coding with AI Studio is so addictive! I built an AI Hair Stylist Agent that: > find the best haircut by looking my face > generates the after images using nano banana > lets me edit it live with the live API > find nearby salons using google maps Built in just 5 mins!

Vibe coding with AI Studio is so addictive! I built an AI Hair Stylist Agent that: > find the best haircut by looking my face > generates the after images using nano banana > lets me edit it live with the live API > find nearby salons using google maps Built in just 5 mins!

Shubham Saboo

46,631 次观看 • 10 个月前

It's not a point and click adventure without VOICE ACTING Here's the full dialogue system with voices for EVERY SINGLE dialogue spoken. > Voice design > Text-to-speech > Background music All using Elevenlabs. Pretty much just one shotted it with their skills. 📣 Sound ON!

It's not a point and click adventure without VOICE ACTING Here's the full dialogue system with voices for EVERY SINGLE dialogue spoken. > Voice design > Text-to-speech > Background music All using Elevenlabs. Pretty much just one shotted it with their skills. 📣 Sound ON!

Chong-U

14,861 次观看 • 2 个月前

Introducing Voice Changer by change your voice into ANYONE else's with just 10 seconds of audio. • One recording --> infinite voices • Preserves emotion and tone • No more hiring voice actors • Works instantly on mobile

Introducing Voice Changer by change your voice into ANYONE else's with just 10 seconds of audio. • One recording --> infinite voices • Preserves emotion and tone • No more hiring voice actors • Works instantly on mobile

PlayAI

101,156 次观看 • 1 年前

Toad unifies your AI coding agents in the terminal with one clean UI, powered by the ACP protocol. Awesome. > uv tool install -U batrachian-toad

Toad unifies your AI coding agents in the terminal with one clean UI, powered by the ACP protocol. Awesome. > uv tool install -U batrachian-toad

Tw93

22,726 次观看 • 7 个月前

That's very impressive You can now use an audio-visual AI model in REAL TIME. So you're not just generating a one-shot video but you can: > interact with it > create a real time character > speak and receive replies Things are moving so fast

That's very impressive You can now use an audio-visual AI model in REAL TIME. So you're not just generating a one-shot video but you can: > interact with it > create a real time character > speak and receive replies Things are moving so fast

Paul Couvert

44,495 次观看 • 2 个月前

With our recent vibe-coding builder for WordPress, 10Web offers the full solution under White Label / API for Agencies & MSPs, Hosting providers and SaaS platforms. Offer full AI Websites to your clients and users with zero dev lift. -> Book your demo

With our recent vibe-coding builder for WordPress, 10Web offers the full solution under White Label / API for Agencies & MSPs, Hosting providers and SaaS platforms. Offer full AI Websites to your clients and users with zero dev lift. -> Book your demo

Arto Minasyan

2,168,315 次观看 • 10 个月前

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

A new milestone for real-time accurate 3D spatial computing! Introducing ⚡️Fast-FoundationStereo⚡️, a real-time zero-shot stereo depth estimation model that accelerates the original FoundationStereo by >10x with comparable quality. Details in threads 🧵 (1/N)

Bowen Wen

77,140 次观看 • 8 个月前

Working with Edge Functions just got a major upgrade: → Function list & search → Copy-paste snippets → Built-in testing → Download as zip Update your self-hosted Supabase instance: >

Working with Edge Functions just got a major upgrade: → Function list & search → Copy-paste snippets → Built-in testing → Download as zip Update your self-hosted Supabase instance: >

Supabase

26,011 次观看 • 6 个月前

Most "AI coding tools" need 5 files, a build config, and a prayer. Gradio 6's gr.HTML: one Python file. Frontend, backend, state—done 😎 Generate with Claude or any frontier LLM in one shot. Deploy in seconds. This is what vibe coding is supposed to be! Full breakdown👇️

Most "AI coding tools" need 5 files, a build config, and a prayer. Gradio 6's gr.HTML: one Python file. Frontend, backend, state—done 😎 Generate with Claude or any frontier LLM in one shot. Deploy in seconds. This is what vibe coding is supposed to be! Full breakdown👇️

Gradio

22,392 次观看 • 6 个月前

Yesterday I built a support agent with Flue for our fake coffee shop (thecoffeecluster) that shows PlanetScale <-> Hyperdrive I just created a new PlanetScale branch and pointed my coding agents to the Flue docs. The result is insane. We live in the future 🔥

Yesterday I built a support agent with Flue for our fake coffee shop (thecoffeecluster) that shows PlanetScale <-> Hyperdrive I just created a new PlanetScale branch and pointed my coding agents to the Flue docs. The result is insane. We live in the future 🔥

Jilles Soeters

12,864 次观看 • 2 个月前

i discovered the dumbest AI hack that saves me 3 hours per project instead of asking AI for "the best" solution i just ask: > Create a test page with 10 variations of this hero section then i pick the best one in 30 seconds why tf did i waste years deciding manually

i discovered the dumbest AI hack that saves me 3 hours per project instead of asking AI for "the best" solution i just ask: > Create a test page with 10 variations of this hero section then i pick the best one in 30 seconds why tf did i waste years deciding manually

Melvyn • Builder

31,845 次观看 • 7 个月前

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)

Day 1 of 3 MLX Releases: Introducing MLX-Audio 🚀🔥 A text-to-speech (TTS) and Speech-to-Speech (STS) library built on Apple's MLX framework, providing efficient speech synthesis on Apple Silicon. Features ⚡️Fast inference on Apple Silicon (M series chips) 🤖Multiple language support 🗣️Voice customization options 🚀Quantization support for optimized performance Supported models: 🪶Kokoro - A multilingual TTS model with 82M params that supports various languages and voice styles. With more models coming soon. Get started: > pip install mlx-audio Please leave us a star and send a PR :)

Prince Canuma

123,553 次观看 • 1 年前

Let's be real: we can't beat AI in speed. So why compete? Instead, let's use it to create something REAL. Meet SkyReels - All-in-one AI Video Creation Platform V3, the world's FIRST AI model for true multi-person conversations! Upload a group photo, assign voices, and generate a video with multiple characters talking naturally. It's not just about being fast, it's about being groundbreaking ➜

Let's be real: we can't beat AI in speed. So why compete? Instead, let's use it to create something REAL. Meet SkyReels - All-in-one AI Video Creation Platform V3, the world's FIRST AI model for true multi-person conversations! Upload a group photo, assign voices, and generate a video with multiple characters talking naturally. It's not just about being fast, it's about being groundbreaking ➜

Eyisha Zyer

35,018 次观看 • 10 个月前

Crunched (Crunched) is the first Excel AI built by and for Excel power users - tailored for consulting and finance workflows. The team has 10k+ hrs in Excel. Crunched is live with firms across Europe & US, with users report being >2x faster on modeling tasks.

Crunched (Crunched) is the first Excel AI built by and for Excel power users - tailored for consulting and finance workflows. The team has 10k+ hrs in Excel. Crunched is live with firms across Europe & US, with users report being >2x faster on modeling tasks.

Y Combinator

2,038,527 次观看 • 10 个月前