Launching today

StillTalk

Launching today

A photo that talks back. Live on your device, not video.

11 followers

A photo that talks back. Live on your device, not video.

11 followers

Visit website

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.

Free

Launch tags:Web App•Developer Tools•Artificial Intelligence

Launch Team / Built With

OpenAI

GPT-6 Astra Challenge

How did Astra change the scope or ambition of what you built?

Maker

Before Astra, this was a feature we kept failing to ship: one talking tutor for our language-learning app. We tried a classic 3D renderer and earlier models; the results never passed visual review. With Astra, the scope grew from one avatar to an engine. Starting September 4, Astra designed and built a browser renderer that animates a single generated photo, a calibration corpus of 980 speech samples in six languages, and a test lab where every new version is checked automatically, frame by frame, against the previous one. I set the quality bar and reviewed frames; Astra did the engineering and turned every correction into an automated check. That made the next step possible. When we found this challenge on September 12, Astra built four more characters in about a day, two of them with very few corrections from me. A feature became StillTalk: a standalone product with a public demo, live speech, and a path to an API and custom characters.

Report

2h ago

Maker

📌

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.

Report

17h ago

Honestly, the talking photo thing is kinda cool. I wonder how natural it looks with different photos.

Report

4m ago