Hammad
@HammadH4
Followers
655
Following
1K
Media
135
Statuses
3K
building @PlayAIOfficial | keep the drum beat going
mv
Joined August 2011
Today we make our first open source contribution - a model that lets you edit speech in audio/video content by simply editing text. Here’s how it works - 1/ upload content 2/ model transcribes speech 3/ you edit transcribed text 4/ model makes changes using the same voice!
🎙️ After serving millions of users through our text-to-speech platform, one need kept coming up: fine-grained AI speech editing - the ability to modify existing speech. Today, we’re open-sourcing PlayDiffusion, a diffusion-based inpainting model built for that exact purpose.
0
0
10
It costs $0.00 to support a 43 year old game developer. 🧑🚀
144
265
4K
Young Steve Jobs riding a motorcycle, getting started from a garage, a true Californian. Greatness often wears jeans, not suits.
96
168
2K
Thrilled to share with the world our flagship voice model - Dialog! Available through api and studio Dialog is the first audio model that can understand the full input text and generate coherent emotional output speech. Great for hq audio content! Try it out and let us know your
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
3
0
8
Incredibly excited and humbled to share that we @play_ht have raised $21M to make voice AI delightful, accessible and useful to all. Super grateful to everyone who supported us. We wouldn't be here without you.
Today, we’re excited to announce $21 million in new capital from @KindredVentures, @RaceCapital, @500GlobalVC, @ycombinator, @Soma_Capital, @pioneer_fund and others to build the future of conversation with real-time voice AI. We’re on a mission to make voice AI platforms simple
4
0
9
😍
The different voices of @play_ht are so good; my biggest project that I am pursuing is creating a Japanese tutor for my trip to Shibuya! 💛 Here is an audio clip that I found good enough after playing with the parameters:
1
0
2
Really fun to see the hidden thoughts: "But wait"
🚀 DeepSeek-R1-Lite-Preview is now live: unleashing supercharged reasoning power! 🔍 o1-preview-level performance on AIME & MATH benchmarks. 💡 Transparent thought process in real-time. 🛠️ Open-source models & API coming soon! 🌐 Try it now at https://t.co/v1TFy7LHNy
#DeepSeek
2
6
93
Generate AI podcasts based on real time news🎙️ I built an app that crawls the web for interesting news stories then records a podcast with my own voice. Powered by Llama 3.1 from @togethercompute, voice cloning from @play_ht, and scraping from @firecrawl_dev. Check it out:
52
136
1K
⚡️⚡️⚡️
PlayDialog (@play_ht) is pretty amazing at synthesizing conversation. Better output than NotebookLM imo.
0
0
1
nice! would love to hear the full version
0
0
1
Today, we're introducing PlayDialog beta. It's a SOTA voice model built for fluid, emotive, human-like conversation. PlayDialog lets you create engaging dialog and speaker narrative programmatically -- and from documents, URLs, or text. Nothing else sounds as human.
13
30
172
Meet Play 3.0 mini⚡️ A new lightweight Multilingual Text-to-Speech model optimized for realtime speed, reliability and cost-efficiency. ✅ speaks 30+ languages ✅ streaming <200ms latency ✅ zero shot cloning ✅ <3% error rate https://t.co/GuvkKJvx4j
Today we’re introducing our latest Text-To-Speech model, Play 3.0 mini. It’s faster, more accurate, handles multiple languages, supports streaming from LLMs, and it’s more cost-efficient than ever before. Try it out here: https://t.co/4xBZ4YlDM1
1
0
4
Just like a website, AI agents that interact with customers will play a crucial role in representing the brand of a business.
1
0
1