One recording, unlimited personal videos. Your product fills in the name, company and reason, and the same real person says it on camera.
Build the script from your own data: name, company, trigger, next step.
Script mode lets you place natural pauses between phrases.
Every video returns word-level timings so you can add captions in your style.
Anywhere your product already sends a message, it can send a face instead.
Requests are asynchronous and independent, so you can queue thousands of videos at once and process results as webhooks arrive. Pricing is per second with no monthly minimum, so cost scales with what you actually send.
No. You fill them in before sending; PitchTwin receives the final text for each video.
Every generation returns words with start and end times. Use them to render captions in your own player or burn them in.
A 45-second video costs 45 tokens with your own audio or about 68 with our voice: roughly $0.56–0.84 on the Scale pack.
Two endpoints and a webhook. Your product creates an avatar from a short video of a real person, then asks for as many videos of them as it needs. No studio, no seats, no watermark.
Most avatar engines re-generate the whole face, and viewers notice the waxy skin and frozen eyes. PitchTwin builds every avatar from real video of the person and keeps that footage, so the result looks like them.
Your customers should only ever see your brand. PitchTwin videos carry no watermark and no mention of us, and they're delivered to your own infrastructure.
Record once in any language. Then have the same person speak to every market, either in their cloned voice or with audio you've already dubbed.