leo retweeted
HeyGen Voice takes the #1 spot on the Artificial Analysis Controlled Voice TTS Arena Leaderboard, ahead of Alibaba's Qwen-Audio-3.1-TTS-Plus and ElevenLabs' Eleven v4 Turbo
HeyGen Voice is the first Text to Speech model from @HeyGen evaluated in our Controlled Voice Arena, where models are evaluated using the same 8 cloned voices across US and UK English.
Key takeaways:
➤ Controlled Voice: HeyGen Voice has an Elo of 1,201 across 1,468 arena appearances, placing it ahead of Qwen-Audio-3.1-TTS-Plus at 1,182, Eleven v4 Turbo at 1,166 and Eleven v4 at 1,162. It ranks #1 in Assistants and Customer Service, #2 in Knowledge Sharing and #1 in English (UK).
➤ Pronunciation Robustness: HeyGen Voice scores 83.1%, ranking #10 of 29 models, behind Qwen-Audio-3.1-TTS-Plus at 84.6% and ahead of Inworld Realtime TTS-2 at 80.7%. It ranks #2 in Preserving Exact Sequences at 83.3%, behind only SpaceXAI TTS.
➤ Pricing: HeyGen Voice is priced at $30/1M characters, compared to Qwen-Audio-3.1-TTS-Plus at $19.3/1M characters, Eleven v4 Turbo at $40/1M characters and Eleven v4 at $80/1M characters.
➤ Speed: HeyGen Voice processes 40 characters per second of generation time, compared to 76 characters per second for Eleven v4 and 46 for Gemini 3.8 Flash TTS.
See more details and listen to samples below ⬇️
leo retweeted
Your agent plans the trip in Gullivr. HeyGen MCP makes the trailer that gets everyone to commit.
Finally, a trip that makes it out of the group chat.
leo retweeted
ChatGPT sets up your Halloween party on @partiful. HeyGen MCP makes your video invite.
One prompt and the whole guest list gets a personal invite from a vampire version of you.
leo retweeted
HeyGen is on the @Forbes AI 50 list
It’s an honor, and a reflection of what we’ve believed from day one: anyone with a message worth sharing deserves the tools to share it
Grateful to our team, customers, and community for making this possible 🙏
forbes.com/lists/ai50/
leo retweeted
We solved character consistency. Forever
Avatar V captures you in 15 seconds and holds your identity across every video.
Change the look, outfit, and setting to create unlimited versions of you.
RT + comment "AvatarV" below and I'll DM 100 credits to test it out (must follow)
leo retweeted
the future of video editing is code-gen.
we started integrating @Remotion into our Video Agent 2 months ago
here are some examples of what our agent put together 🧵
leo retweeted
Today, we are proud to introduce LiveAvatar by HeyGen. It was built alongside visionary customers already using it to shape the future of AI.
LiveAvatar offers hyper-realistic, real-time interactive avatars that enable face-to-face human conversation experiences on demand, and at scale.
Check out how visionaries like @reidhoffman are redefining human-AI interaction with LiveAvatar.
Learn more at liveavatar.com
What a fun journey it has been! So much more to come!
HeyGen just hit $100M ARR this month, 29 months after we first reached $1M in April 2023.
None of this happens without our incredible team, customers, partners, and community. Thank you 💜
When we shared our first $1M milestone, it was to give back to the build-in-public community. The AI landscape has changed completely since then, but one thing hasn’t: how we build.
Internally, we’ve called it our “bible,” the system that’s guided us from $1M to $100M. It’s built from countless team discussions, experiments, and lessons learned along the way. After much reflection, I wanted to document what’s worked for us — for our team and for everyone building in AI.
We’re sharing it not because it’s perfect, but because it’s working. It’s how we deliver customer value, learn faster than the world changes, and keep riding the wave.
This is The HeyGen Way.
leo retweeted
Your Digital Twin is now indistinguishable from you.
Today, I’m proud to announce that HeyGen Digital Twin is now powered by Avatar IV, the world’s most advanced avatar model.
Your Digital Twin now:
✅Mirrors your gestures, expressions, and mannerisms
✅Adapts to your script, speaking every line how you would
✅Moves like you, naturally, from head to toe
✅Feels unmistakably you, not AI
For the first time, you can create videos that look, sound, and feel like the real you without the stress of filming or endless retakes.
This is more than convenience. It is the edge every creator, entrepreneur, service provider and executive has been waiting for.
Whether you are building a brand, educating customers, or reaching new audiences, your Digital Twin makes it seamless.
Grow your presence without sacrificing your time. Focus on what you do best. Your Digital Twin handles the rest.
⚡ Available now on HeyGen.
Truly mind blowing how easy it is to create high quality, polished videos now🤯
Today we’re introducing you to the future of video.
The world’s first Creative Operating System, we call it the HeyGen Video Agent.
Upload a doc, some footage, or even just a sentence.
It analyzes your input.
Finds the story.
Writes the script with taste.
Selects the shots or generates the footage.
Casts your actor.
And edits everything… Pacing. Motion. Captions.
An entire creative team built to tell your story.
Whether it’s ads, TikToks, short films, product demos, or any other idea you’re dreaming up.
Join the waitlist below. 👇
leo retweeted
Product Placement has landed at HeyGen.
Upload your product photo, choose an avatar, drop in your script- and boom, you’ve got a scroll-stopping UGC ad.
Powered by Avatar IV’s hyper-realistic gestures and lip-sync.
No studio. No actors. No editing.
Now available to everyone on HeyGen.
What product are you trying first?👇
🤯🤯🤯
🆕 NEW: HeyGen Avatar IV is here.
Our most advanced AI avatar model yet.
📸 One photo.
📝 One script.
🎧 Just your voice.
Most avatars sync to your words. Avatar IV interprets them.
Built on a diffusion-inspired audio-to-expression engine, it analyzes your vocal tone, rhythm, and emotion — then synthesizes photoreal facial motion with temporal realism.
🎭 Head tilts. Pauses. Cadences. Micro-expressions.
➡️ A single image → a video that feels real, not rendered.
Rolling out to all users now.
👇 See examples and what makes it different