Loading video...

Video Failed to Load

Go Home

Hindi Speech Model should be free and open-source. And we’re making it happen. >High quality >Multiple voices >UI to generate audio + API for deployment Follow me to get notified when it launches. Listen to the audio till the end!

Dheemanthredy's profile picture

Dheemanth Reddy

9,395 subscribers

59,738 views • 1 year ago •via X (Twitter)

News & PoliticsScience & TechnologyEducation
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

We're making building with the text-to-speech API even easier by adding it to the Playground! Just enter a message to generate audio in one of six preset voices.
0:16

We're making building with the text-to-speech API even easier by adding it to the Playground! Just enter a message to generate audio in one of six preset voices.

OpenAI Developers

125,130 views • 2 years ago

Breaking: Pika launches the first near-real-time HD audio-driven performance model > Selfie + sound clip -> hyper-realistic, expressive videos > Works in any style: photorealistic, anime, pixel art, fantasy > 6 sec to generate, 20x faster & cheaper 9 Impressive examples 👇
0:15

Breaking: Pika launches the first near-real-time HD audio-driven performance model > Selfie + sound clip -> hyper-realistic, expressive videos > Works in any style: photorealistic, anime, pixel art, fantasy > 6 sec to generate, 20x faster & cheaper 9 Impressive examples 👇

AshutoshShrivastava

14,789 views • 11 months ago

Wan 2.2 Speech-to-Video 14B just landed > audio-driven cinematic video generation > weights & demo on the hub > apache 2.0 license + looks like it could be compatiable with Wan 2.x LoRAs out-of-the-box
0:12

Wan 2.2 Speech-to-Video 14B just landed > audio-driven cinematic video generation > weights & demo on the hub > apache 2.0 license + looks like it could be compatiable with Wan 2.x LoRAs out-of-the-box

Linoy Tsaban🎗️

13,057 views • 11 months ago

Love when the high low is executed from a big to a guard >>> Kalani Brown dishes it off to Celeste Taylor 🫡 LVA-PHX | Watch FREE on the WNBA APP
0:12

Love when the high low is executed from a big to a guard >>> Kalani Brown dishes it off to Celeste Taylor 🫡 LVA-PHX | Watch FREE on the WNBA APP

WNBA

11,736 views • 1 year ago

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality
0:14

Stable Audio 3 by Stability AI is just out It mainly comes with 3 open source variants: - Stable Audio 3 Medium (2B) - Stable Audio 3 Small (0.6B) - Music - Stable Audio 3 Small (0.6B) - VFX (and a "large" closed variant) The open models are really fast and high quality

apolinario (poli)

41,529 views • 2 months ago

NVIDIA's PiD is a new pixel diffusion decoder for high-res image models. It skips decode-then-upscale stop, making sharper outputs faster. > Directly generates 4K images > Up to 5.9x faster than SeedVR2 > Free & open weights
0:15

NVIDIA's PiD is a new pixel diffusion decoder for high-res image models. It skips decode-then-upscale stop, making sharper outputs faster. > Directly generates 4K images > Up to 5.9x faster than SeedVR2 > Free & open weights

⚡AI Search⚡

14,706 views • 2 months ago

There’s just something about a tropical brunette ❤️🍓well-built, stunning, and dangerously hard to ignore >>>> Just watch till the end ❤️🍓
0:14

Sensitive content

There’s just something about a tropical brunette ❤️🍓well-built, stunning, and dangerously hard to ignore >>>> Just watch till the end ❤️🍓

𝑩☥𝒈 𝑺𝒕𝒖𝒏𝒏𝒂 🥷

60,592 views • 7 months ago

“Even though each of us is very active with our solo activities, we’ve talked a lot among the members about putting the team first as a priority. When it’s time for us to work as a group, we should really do it and prioritize it more.” ㅡ Chanyeol, 2025 his loyalty >>>>>>>>
0:16

“Even though each of us is very active with our solo activities, we’ve talked a lot among the members about putting the team first as a priority. When it’s time for us to work as a group, we should really do it and prioritize it more.” ㅡ Chanyeol, 2025 his loyalty >>>>>>>>

알찬열매🍒ZURUIYO ㅡ UPSIDE DOWN 2ND ALBUM ENTHUSIAST

43,168 views • 7 months ago

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇
0:12

We've got a new audio-conditioned video model 👀 LTX Studio now lets you upload or generate audio, and then creates a lip-synced video. This is going to be HUGE for consistent character voices + AI influencers. I tested it w/ an animation of my pets. More on how to use it 👇

Justine Moore

18,562 views • 6 months ago

Holy smoke... Hunyuan3D 2.0 MV is impressive (and open source 🫨) ➡️ You can generate a mesh from multiple images in just seconds. Next workflow: effortlessly create a consistent turnaround on Scenario > then generate the mesh from it.
0:16

Holy smoke... Hunyuan3D 2.0 MV is impressive (and open source 🫨) ➡️ You can generate a mesh from multiple images in just seconds. Next workflow: effortlessly create a consistent turnaround on Scenario > then generate the mesh from it.

Emm | scenario.com

42,015 views • 1 year ago

Chat GPT 4o released their API it is INSANE for static ads! We made a tool to generate 10 static ads in one click: > upload a reference image > write your prompt > get 10 static ads in 2min It's live today! Comment Arcads to get early access 👇
0:14

Chat GPT 4o released their API it is INSANE for static ads! We made a tool to generate 10 static ads in one click: > upload a reference image > write your prompt > get 10 static ads in 2min It's live today! Comment Arcads to get early access 👇

Romain Torres

44,044 views • 1 year ago

People that actually think outside the box >>>>>> This is a breath of fresh air from the usual they want to use and finish us. The fact that it looks appetizing....I rate it a 💯 abeg Would you be willing to try this out?
0:13

People that actually think outside the box >>>>>> This is a breath of fresh air from the usual they want to use and finish us. The fact that it looks appetizing....I rate it a 💯 abeg Would you be willing to try this out?

NaijaFarmer

34,503 views • 7 months ago

> Don't be like Sourav Joshi > Treat wife as cameraman > Ignore her > Used her for views and content creation > Actually doesn't love her > Don't listen to her > No love seen from him till now Everything seems like a formality
0:12

> Don't be like Sourav Joshi > Treat wife as cameraman > Ignore her > Used her for views and content creation > Actually doesn't love her > Don't listen to her > No love seen from him till now Everything seems like a formality

Jerry

194,708 views • 7 months ago

>> 7777 followers song cover production raffle [ RT+follow to enter ][ ends nov 10th ] i'm VESEN and i'm an all-rounder cover producer and audio engineer, vocaloid/EDM being my forte. for this raffle, i will be in charge of audio as well as motion graphics! ↓ info in thread ↓
0:20

>> 7777 followers song cover production raffle [ RT+follow to enter ][ ends nov 10th ] i'm VESEN and i'm an all-rounder cover producer and audio engineer, vocaloid/EDM being my forte. for this raffle, i will be in charge of audio as well as motion graphics! ↓ info in thread ↓

VESEN 🔳

70,282 views • 2 years ago

This popular streamer, Duke Dennis and his love for Beyoncé>>> “You don’t listen to Beyoncé? Then who the fuck do you listen to” 🤣👏👏👏
0:17

This popular streamer, Duke Dennis and his love for Beyoncé>>> “You don’t listen to Beyoncé? Then who the fuck do you listen to” 🤣👏👏👏

IChooseViolence

15,180 views • 2 months ago

Early down -> get single high and a 5 man rush -> isolation to AJ Brown on the outside
0:12

Early down -> get single high and a 5 man rush -> isolation to AJ Brown on the outside

Shawn Syed

14,645 views • 9 months ago

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.
0:17

Big moment for text-to-speech. Qwen just open-sourced a text-to-speech model that lets you clone voices, design new ones, and control speech using natural language. Let me explain what I mean: You can literally tell it "speak in a cheerful tone with slight nervousness," and it actually does that. No complex audio engineering needed. What makes this special: - 3-second voice cloning - Covers 10 languages: English, German, French, and more - Latency as low as 97ms for real-time applications - Supports both streaming and non-streaming generation The model comes in two sizes (0.6B and 1.7B parameters), so you can pick based on your hardware and quality needs. Three modes to work with: 1. Custom Voice: Use pre-built premium voices with instruction-based style control 2. Voice Design: Describe the voice you want in plain English (or Chinese), and the model creates it 3. Voice Clone: Provide a 3-second reference audio and clone that voice The best part? It integrates with vLLM for production deployment and has a simple Python package you can pip install. I've shared a link to the GitHub repo in the next tweet.

Akshay 🚀

31,249 views • 6 months ago

> got a model and extracted its vertices > placed particles there and made them luminous > got another model and repeated the steps > morphed between those 2 > had fun might take a while to host this one on my project, but feel free to explore my other works in the 1st reply⬇️
0:17

> got a model and extracted its vertices > placed particles there and made them luminous > got another model and repeated the steps > morphed between those 2 > had fun might take a while to host this one on my project, but feel free to explore my other works in the 1st reply⬇️

Sarlloc ✭

143,850 views • 1 year ago

That feeling when he calms your nervous system and you no longer feel the need to be strong anymore >>>>
0:15

That feeling when he calms your nervous system and you no longer feel the need to be strong anymore >>>>

BIG CHU

23,271 views • 4 months ago