🚀 AI News • Tools • Tutorials 💡 Making AI Simple, Practical & Useful 🤝 Brand Collabs • Promotions • Partnerships 📩 [email protected]
New York, USA
Joined July 2014
- Tweets15.5K
- Following371
- Followers17K
- Likes1.1K
Pinned Tweet
Bell sounds were always where AI SFX got harsh at the top. Tried a gong in ElevenLabs SFX v3 and it rang out without the crunch.
🤝 Paid partnership
Big scenes rarely come down to one sound, so we built SFX v3 to handle more than ever.
Our latest model lets you create richer, more precise sound effects from a single text prompt, with improved music and vocals.
Now available inside @ElevenCreative and ElevenAPI.
This is the kind of work that could make @voicearena_ai a reference point, not just a ranking page. Define the question, publish the test, invite people to challenge it.
Drop 2/15
Are we actually measuring the things we ultimately want our voice AI models to achieve?
The best AI voices are becoming hard to tell apart.
From each other. Not from humans.
🚀 Introducing Turing TTS: an evaluation that measures how often human listeners mistake AI-generated speech for real human speech.
We tested leading TTS models against real human speech. Even the best model fooled listeners only ~10% of the time.
With Turing TTS, we hope to contribute to a broader discussion within the research community about how we measure progress in voice AI.
If one of our goals is to develop speech that is indistinguishable from human speech, how well do our current evaluation methods capture progress toward that goal?
We don’t claim that Turing TTS is the right way forward, or that human indistinguishability should be the goal of every TTS system.
Rather, we hope these findings encourage the community to collectively examine whether blind pairwise human evaluations of naturalness are sufficient, and what else we might need to measure.
Results are now live on @voicearena_ai.
Learn Ai retweeted
Drop 2/15
Are we actually measuring the things we ultimately want our voice AI models to achieve?
The best AI voices are becoming hard to tell apart.
From each other. Not from humans.
🚀 Introducing Turing TTS: an evaluation that measures how often human listeners mistake AI-generated speech for real human speech.
We tested leading TTS models against real human speech. Even the best model fooled listeners only ~10% of the time.
With Turing TTS, we hope to contribute to a broader discussion within the research community about how we measure progress in voice AI.
If one of our goals is to develop speech that is indistinguishable from human speech, how well do our current evaluation methods capture progress toward that goal?
We don’t claim that Turing TTS is the right way forward, or that human indistinguishability should be the goal of every TTS system.
Rather, we hope these findings encourage the community to collectively examine whether blind pairwise human evaluations of naturalness are sufficient, and what else we might need to measure.
Results are now live on @voicearena_ai.
Learn Ai retweeted
Swap any character in your existing footage with Recast.
Everything else stays the exact same. It’s almost scary.
Try it now on ElevenCreative.
Learn Ai retweeted
Bell sounds were always where AI SFX got harsh at the top. Tried a gong in ElevenLabs SFX v3 and it rang out without the crunch.
🤝 Paid partnership
Big scenes rarely come down to one sound, so we built SFX v3 to handle more than ever.
Our latest model lets you create richer, more precise sound effects from a single text prompt, with improved music and vocals.
Now available inside @ElevenCreative and ElevenAPI.
Learn Ai retweeted
Flova 1.5 | One Chat with Multiple Skills
One project. Multiple Skills.
Bring different Skills together in one creation!
- You set the goal. Agent plans the workflow.
- Mix and match Skills to explore different stories and styles.
- Refine your creations and take your ideas even further.
✨ Mix and Match Skills. Turn your ideas into videos, your way!
One conversation can now support a much richer creative process. flova.ai/?refCode=JMCJVVYT
Flova 1.5 | One Chat with Multiple Skills
One project. Multiple Skills.
Bring different Skills together in one creation!
- You set the goal. Agent plans the workflow.
- Mix and match Skills to explore different stories and styles.
- Refine your creations and take your ideas even further.
✨ Mix and Match Skills. Turn your ideas into videos, your way!
Learn Ai retweeted
Big scenes rarely come down to one sound, so we built SFX v3 to handle more than ever.
Our latest model lets you create richer, more precise sound effects from a single text prompt, with improved music and vocals.
Now available inside @ElevenCreative and ElevenAPI.
🤖 Made with AI
can Teamily's shared context also explain to my team what we decided last week
🤝 Paid partnership
The shared context for your personal and team agents to get work done, smarter and faster.
• Run on any device
• Create any type of artifact
• Chat anywhere
• Work anytime
#SharedContext #TeamAgents #TeamilyAI #iPhoneDuo
Your creative process deserves time to develop. Flova 1.5's promotion gives you two years of Pro for the price of one, with the freedom to gift the extra year.
Seedance 2.5 720p starts at $0.025/sec.
flova.ai/?refCode=3BFU8P57
For the creators who have 17 ideas saved and somehow still don’t know what to post today. 🙋
Dreamina’s first month is only $0.29, and CapCut Desktop has 60% off Pro or 40% off Ultra from Oct 20–30. The two tools have separate subscriptions and pricing. Pick one idea, generate the visuals in Dreamina, then move them into CapCut PC to organize the timeline, adjust clip timing, add transitions, and finish the captions and audio. You don’t have to make everything at once—just get one good idea across the finish line.
🔗 CapCut deal: tinyurl.com/2v23rn22
🔗 Dreamina: tinyurl.com/5xbtv4x6
#CapCutDidThat #Dreamina #Smallbusinessmarketing #CapCutSale
Learn Ai retweeted
More and more, image models get ranked by human vote. A vote can miss that your font changed.
Today @DavidZats and I are releasing VybBench, an open benchmark that scores design fidelity with numbers instead of votes. Ask a model to change one headline and it can nudge your font, shift your blue and redraw a corner of your logo too. Each edit changes a little more, until the design isn't yours.
VybBench scores each piece:
145 fonts, matched pixel by pixel against the real font
100 hex codes, scored on how far each color drifts
200 small edits, scored on how many pixels changed, with a judge checking the edit was made
We are not including model scores in the post, but you can see how each model scores on the Hugging Face. Every prompt, output, judge verdict and the scorer is on Hugging Face, link in the reply.
Full Disclosure: At @cocoailabs we also build Vyb - our first design model built to preserve design fidelity and taste.
Sometimes the best upgrade is simply getting more time with the tools you like.
Flova 1.5 is launching with two years of Pro for the price of one. Keep the second year for your own creative plans or share it with a friend. Seedance 2.5 720p starts at $0.025 per second.
Available Oct 27–Nov 30.
flova.ai/?refCode=3BFU8P57
Sometimes the shortest route to a great result is a few detours.
Flova 1.5 makes those detours easier to manage. Explore a different concept in a separate conversation, keep your main project context connected, and return to the original direction whenever you want.
Try the unexpected approach. Revisit the original plan. Let the best idea win.
Start exploring: flova.ai/?refCode=6RTSP48F
One project. More than one task.
One project, multiple conversations, more creative freedom!
- With Flova 1.5, run independent sessions for different creative goals
- Explore ideas in different directions with shared project context
- Switch conversations anytime and pick up where you left off
✨Turn ideas into videos, your way!
Learn Ai retweeted
One project. More than one task.
One project, multiple conversations, more creative freedom!
- With Flova 1.5, run independent sessions for different creative goals
- Explore ideas in different directions with shared project context
- Switch conversations anytime and pick up where you left off
✨Turn ideas into videos, your way!
🤖 Made with AI
Riverside Agents takes a recording from first cut to live post as one crew. The handoffs between stages are where my process leaks time. @RiversidedotFM
🤝 Paid partnership
Meet Riverside Agents, the first AI production team built only for video.
Producer preps the session, Editor creates the full edit, Clipper cuts the best moments, and Marketer gets it live.
They’re experts at video and know how to take your content to the next level. You call the shots.
Watch the demo:
Learn Ai retweeted
Meet Riverside Agents, the first AI production team built only for video.
Producer preps the session, Editor creates the full edit, Clipper cuts the best moments, and Marketer gets it live.
They’re experts at video and know how to take your content to the next level. You call the shots.
Watch the demo: