StillTalk turns one generated photo into a character that talks. Your device draws every frame live in the browser; the server sends only speech and compact movement data. Five characters, six languages, or type your own sentence. No signup. Engine built with GPT-6 Astra.
Hi Product Hunt 👋 I'm Piotr, founder of StillTalk.
StillTalk turns one generated photo into a character that talks, and it is not video. Your device draws every frame live in the browser. The server sends only speech and compact movement data: no video stream, no cloud renderer billing by the minute.
Try it now, no signup: pick one of five characters, one of six languages, play a tongue twister, or type your own sentence and hear it spoken.
The Astra story: GPT-6 Astra designed and implemented the rendering engine, the articulation, the calibration and the tests. My job was to set the quality bar and keep saying "not yet": a blink sitting too high, a mouth shape that worked in Polish but not in French. We found this challenge on Saturday, September 12. The engine worked with one character. Over the next day Astra built four more, and two of them needed very few corrections from me, because every earlier fix had already become an automated check.
For scale: 1.8B+ tokens in the StillTalk thread alone, and 817M on our busiest single day. That includes reused context. It measures the work, not a bill.
Honest limits: live typing runs on a free speech pool with per-person limits. If it runs out, every prepared line still plays.
Next: a commercial API, a wider character library, and a beta for creating a character from your own photo.
This is the result of one very intense sprint. I'm happy with where it is, and I'm still calibrating every day, so it will only get better from here.
I'd love your feedback: which character feels most alive, and where does the lip-sync break in your language? I'm here all day.
Thank you to everyone who watched, listened, voted and asked questions yesterday. For a first launch with no audience behind it, this was a great day, and your questions told me exactly what people want from StillTalk.
Here is what I'm working on:
More alive. Lip-sync tuned per character, subtler face movement while speaking, head turns and glances to the side and up, then a livelier body: gestures, a wave, changes of pose.
Open to builders. A studio where you set the parameters yourself, and an API.
More to choose from. More voices, more languages, more characters.
Your own character, created from a photo or a prompt.
And one from your comments: export to video. @kyle_bennett6 and @charlotte_reed1 both saw StillTalk as a way to make short character clips. It stays a live engine first, but saving a performance as a video is a natural side feature (it's how the launch film was made), so it's on the list. Thank you both.
No dates yet. I'd rather ship each step working than ship it fast. The bigger milestones will come back to Product Hunt as new launches.
Until then the demo stays open: pick a character on stilltalk.ai, type your own line, and leave your email if you want to hear when the next step lands.
Comments and suggestions are always welcome, here or through the contact page on stilltalk.ai.
This could be fun for making little character videos. Curious what people are using it for so far.
I could see this being useful for quick videos when you don’t want to record yourself. Pretty simple idea, but I like it.
The language support is interesting. Does the lip sync stay accurate when you switch between languages?
Honestly, the talking photo thing is kinda cool. I wonder how natural it looks with different photos.
About StillTalk on Product Hunt
“A photo that talks back. Live on your device, not video.”
StillTalk launched on Product Hunt on September 18th, 2026 and earned 66 upvotes and 10 comments, placing #34 on the daily leaderboard. StillTalk turns one generated photo into a character that talks. Your device draws every frame live in the browser; the server sends only speech and compact movement data. Five characters, six languages, or type your own sentence. No signup. Engine built with GPT-6 Astra.
StillTalk was featured in Web App (123.8k followers), Developer Tools (519.8k followers), Artificial Intelligence (479.1k followers) and OpenAI Day (39 followers) on Product Hunt. Together, these topics include over 246.1k products, making this a competitive space to launch in.
Who hunted StillTalk?
StillTalk was hunted by Piotr Janik. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
Want to see how StillTalk stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
Piotr Janik
Hi Product Hunt 👋 I'm Piotr, founder of StillTalk.
StillTalk turns one generated photo into a character that talks, and it is not video. Your device draws every frame live in the browser. The server sends only speech and compact movement data: no video stream, no cloud renderer billing by the minute.
Try it now, no signup: pick one of five characters, one of six languages, play a tongue twister, or type your own sentence and hear it spoken.
The Astra story: GPT-6 Astra designed and implemented the rendering engine, the articulation, the calibration and the tests. My job was to set the quality bar and keep saying "not yet": a blink sitting too high, a mouth shape that worked in Polish but not in French. We found this challenge on Saturday, September 12. The engine worked with one character. Over the next day Astra built four more, and two of them needed very few corrections from me, because every earlier fix had already become an automated check.
For scale: 1.8B+ tokens in the StillTalk thread alone, and 817M on our busiest single day. That includes reused context. It measures the work, not a bill.
Honest limits: live typing runs on a free speech pool with per-person limits. If it runs out, every prepared line still plays.
Next: a commercial API, a wider character library, and a beta for creating a character from your own photo.
This is the result of one very intense sprint. I'm happy with where it is, and I'm still calibrating every day, so it will only get better from here.
I'd love your feedback: which character feels most alive, and where does the lip-sync break in your language? I'm here all day.