--- title: I created an interactive digital avatar of myself — and... description: A TechCrunch reporter recounts getting an interactive AI avatar made by Synthesia, a video-generation startup valued at $4 billion with over $100 million in... canonical: https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1 twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: I created an interactive digital avatar of myself — and you can talk to it | daily.dev og:description: A TechCrunch reporter recounts getting an interactive AI avatar made by Synthesia, a video-generation startup valued at $4 billion with over $100 million in... og:url: https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1 og:image: https://api.daily.dev/og/posts/trZNf7YU1.png og:image:alt: I created an interactive digital avatar of myself — and you can talk to it og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # I created an interactive digital avatar of myself — and you can talk to it **[TechCrunch](https://daily.dev/sources/tc)** · 7 min read · 0 upvotes · 0 comments ## Summary A TechCrunch reporter recounts getting an interactive AI avatar made by Synthesia, a video-generation startup valued at $4 billion with over $100 million in ARR. The avatar, built from photos and a voice sample, uses a deterministic pipeline of voice-to-text, an agentic language model, text-to-voice, and a video model, and only answers questions about a specific trained article. The piece reflects on the creepiness, novelty, and implications of digital twins for journalism and corporate use, including Synthesia's Roleplay Sessions product for training. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### How does Synthesia's interactive avatar technology work under the hood? It combines four models in sequence: a voice-to-text model converts spoken input into text, an agentic language model interprets the text and determines a response, a text-to-voice model converts that response into audio, and a video model built by Synthesia animates the avatar's face and mouth to match. Synthesia's own video and voice models power the stack by default, though customers can substitute providers like Cartesia, ElevenLabs, Google, or OpenAI. _Developers building conversational avatar pipelines can compare model stacks and voice AI options on daily.dev._ ### What is the difference between a deterministic and nondeterministic AI avatar? A deterministic avatar only responds with pre-trained answers tied to specific content, such as one article, and redirects any off-topic question back to that material, making it incapable of improvising. A nondeterministic avatar is powered by a freeform chatbot that can generate novel responses on the fly, which carries more risk of unpredictable or unsettling behavior, sometimes described as contributing to a feeling akin to AI psychosis. _Anyone evaluating chatbot-driven versus scripted AI agents can track these design tradeoffs on daily.dev._ ## Similar posts on daily.dev - [Synthesia’s AI training platform is moving beyond videos into live coaching](https://daily.dev/posts/synthesia-s-ai-training-platform-is-moving-beyond-videos-into-live-coaching-opn3xpf0k) · TechCrunch · 0 upvotes · 0 comments --- Tags: [#genai](https://daily.dev/tags/genai) [View this post on daily.dev](https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"I created an interactive digital avatar of myself — and you can talk to it","url":"https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1"},"datePublished":"2026-09-26T14:01:37.376Z","dateModified":"2026-09-26T14:02:04.183Z","description":"A TechCrunch reporter recounts getting an interactive AI avatar made by Synthesia, a video-generation startup valued at $4 billion with over $100 million in...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d82136817d1db6562bf4d024ad4b1e6d?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/d82136817d1db6562bf4d024ad4b1e6d?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"TechCrunch","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"TechCrunch","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/tc","url":"https://daily.dev/sources/tc"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"genai","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"TechCrunch","item":"https://daily.dev/sources/tc"},{"@type":"ListItem","position":3,"name":"I created an interactive digital avatar of myself — and you can talk to it"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/i-created-an-interactive-digital-avatar-of-myself-and-you-can-talk-to-it-trznf7yu1#faq","mainEntity":[{"@type":"Question","name":"How does Synthesia's interactive avatar technology work under the hood?","acceptedAnswer":{"@type":"Answer","text":"It combines four models in sequence: a voice-to-text model converts spoken input into text, an agentic language model interprets the text and determines a response, a text-to-voice model converts that response into audio, and a video model built by Synthesia animates the avatar's face and mouth to match. Synthesia's own video and voice models power the stack by default, though customers can substitute providers like Cartesia, ElevenLabs, Google, or OpenAI. Developers building conversational avatar pipelines can compare model stacks and voice AI options on daily.dev."}},{"@type":"Question","name":"What is the difference between a deterministic and nondeterministic AI avatar?","acceptedAnswer":{"@type":"Answer","text":"A deterministic avatar only responds with pre-trained answers tied to specific content, such as one article, and redirects any off-topic question back to that material, making it incapable of improvising. A nondeterministic avatar is powered by a freeform chatbot that can generate novel responses on the fly, which carries more risk of unpredictable or unsettling behavior, sometimes described as contributing to a feeling akin to AI psychosis. Anyone evaluating chatbot-driven versus scripted AI agents can track these design tradeoffs on daily.dev."}}]} ```