Syren: Make a Whole Video From One Prompt With Synthesia's New AI Video Agent
Synthesia's new Syren (in beta) writes a video as code and renders it while you watch: motion graphics, 3D, voiceover, music and avatars from one prompt, refined in a chat. How to start, what the free launch credits cover, what a video costs after that, and what it can't do yet
Most AI video tools give you a loose clip you still have to cut, voice and score yourself. Syren starts from one prompt and builds the whole video: the visuals, the voiceover, the music and, if you want one, an avatar.
It's from Synthesia, the company behind the AI avatar videos you've seen in corporate training. Everything below is from Synthesia's own page, read on October 9, 2026. I haven't run Syren myself, so treat the details as Synthesia's claims until you've tried it.
Make your first Syren video
- Describe the video in your own words. You can also add docs, images, videos, PowerPoints or YouTube links, or start from a preset use case.
- Watch it build. Syren writes the video as code and renders it while you watch.
- Refine it in the chat: change the script, swap the avatar or the voice, or restyle one scene.
- Choose landscape for websites and slides or portrait for phones and social. Videos can run up to three minutes.
A good first prompt is the one Syren's own showreel types on screen:
a 30-second welcome video for new hires
Keep reading
Free, for an email.
Unlocks 5 more sections, the document version, and every other guide on the site, for free. Enter your email once to keep reading.
19,000+ follow where these guides come from.No spam. Unsubscribe in one click.