--- title: Gemini 3.8 text-to-speech says hello | daily.dev description: Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models offering generative voice design, a library of 2,000+... canonical: https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Gemini 3.8 text-to-speech says hello | daily.dev og:description: Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models offering generative voice design, a library of 2,000+... og:url: https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu og:image: https://api.daily.dev/og/posts/aCCW7wwqU.png og:image:alt: Gemini 3.8 text-to-speech says hello 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. # Gemini 3.8 text-to-speech says hello **[DeepMind](https://daily.dev/sources/dm)** · 6 min read · 0 upvotes · 0 comments ## Summary Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models offering generative voice design, a library of 2,000+ voices, voice replication from a 30-second sample, long-form and dual-speaker scene generation, and line-by-line performance direction with non-verbal cues like laughs and sighs. Flash TTS targets deep creative control for gaming, audiobooks, and podcasts, while Flash-Lite TTS targets high-volume, cost-efficient dubbing and voice agents. Gemini 3.8 Flash TTS ranks #1 on Hume AI's Voice Design Benchmark and Overall Quality Index, with Flash-Lite ranking #2. Both models include SynthID watermarking and consent verification for voice replication, and are rolling out via the Gemini API, Google AI Studio, Gemini Notebook, Google Vids, and soon Gemini Enterprise. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Questions this post answers ### What new text-to-speech models did Google release with Gemini 3.8? Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. Flash TTS supports generative voice design, a 2,000+ voice library, voice replication from a 30-second sample, and line-by-line performance direction with non-verbal cues; Flash-Lite TTS targets high-volume, cost-efficient dubbing and voice agents. Both are available via the Gemini API and Google AI Studio. _Developers evaluating TTS options for voice agents can track Gemini audio model updates on daily.dev._ ### How does Gemini 3.8 Flash TTS compare to other text-to-speech models in quality benchmarks? Gemini 3.8 Flash TTS holds the #1 overall spot on Hume AI's Voice Design Benchmark with a score of 71.4, and leads accent modeling with 60.8. It also ranks #1 on Hume AI's Overall Quality Index, with Gemini 3.8 Flash-Lite TTS ranking #2, and both top Voice Arena's blind preference tests in languages like Japanese, Brazilian Portuguese, and Hindi. _Teams comparing TTS providers can follow benchmark results like these on daily.dev before choosing a model._ ### What safeguards does Gemini's voice replication feature use to prevent misuse? Voice replication requires consent verification: users must submit a verbal consent recording from the voice owner matching the reference speaker before a voice can be created. Every generated audio clip is also watermarked with SynthID, an imperceptible marker woven into the output, plus C2PA credentials, to keep AI-generated speech detectable and protect voice talent from unauthorized use. _Developers building voice-cloning features can weigh consent and watermarking requirements discussed on daily.dev._ ## Similar posts on daily.dev - [Gemini 3.1 Flash TTS: the next generation of expressive AI speech](https://daily.dev/posts/gemini-3-1-flash-tts-the-next-generation-of-expressive-ai-speech-1av40deos) · DeepMind · 9 upvotes · 1 comments - [Gemini 3.1 Flash TTS on Google Cloud](https://daily.dev/posts/gemini-3-1-flash-tts-on-google-cloud-pl4nonfnc) · Google Cloud · 0 upvotes · 0 comments - [Improved Gemini audio models for powerful voice interactions](https://daily.dev/posts/improved-gemini-audio-models-for-powerful-voice-interactions-nxigikvvz) · DeepMind · 0 upvotes · 0 comments --- Tags: [#google](https://daily.dev/tags/google), [#google-gemini](https://daily.dev/tags/google-gemini), [#text-to-speech](https://daily.dev/tags/text-to-speech), [#voice-cloning](https://daily.dev/tags/voice-cloning), [#google-ai-studio](https://daily.dev/tags/google-ai-studio) [View this post on daily.dev](https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu) ```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":"Gemini 3.8 text-to-speech says hello","url":"https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu"},"datePublished":"2026-09-30T20:06:22.598Z","dateModified":"2026-09-30T20:07:02.175Z","description":"Google introduced Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS, two new text-to-speech models offering generative voice design, a library of 2,000+...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f5642655f1894662a0202460a2e2b68?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/8f5642655f1894662a0202460a2e2b68?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"DeepMind","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":"DeepMind","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/dm","url":"https://daily.dev/sources/dm"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"google,google-gemini,text-to-speech,voice-cloning,google-ai-studio","timeRequired":"PT6M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"DeepMind","item":"https://daily.dev/sources/dm"},{"@type":"ListItem","position":3,"name":"Gemini 3.8 text-to-speech says hello"}]} {"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/gemini-3-8-text-to-speech-says-hello-accw7wwqu#faq","mainEntity":[{"@type":"Question","name":"What new text-to-speech models did Google release with Gemini 3.8?","acceptedAnswer":{"@type":"Answer","text":"Google released Gemini 3.8 Flash TTS and Gemini 3.8 Flash-Lite TTS. Flash TTS supports generative voice design, a 2,000+ voice library, voice replication from a 30-second sample, and line-by-line performance direction with non-verbal cues; Flash-Lite TTS targets high-volume, cost-efficient dubbing and voice agents. Both are available via the Gemini API and Google AI Studio. Developers evaluating TTS options for voice agents can track Gemini audio model updates on daily.dev."}},{"@type":"Question","name":"How does Gemini 3.8 Flash TTS compare to other text-to-speech models in quality benchmarks?","acceptedAnswer":{"@type":"Answer","text":"Gemini 3.8 Flash TTS holds the #1 overall spot on Hume AI's Voice Design Benchmark with a score of 71.4, and leads accent modeling with 60.8. It also ranks #1 on Hume AI's Overall Quality Index, with Gemini 3.8 Flash-Lite TTS ranking #2, and both top Voice Arena's blind preference tests in languages like Japanese, Brazilian Portuguese, and Hindi. Teams comparing TTS providers can follow benchmark results like these on daily.dev before choosing a model."}},{"@type":"Question","name":"What safeguards does Gemini's voice replication feature use to prevent misuse?","acceptedAnswer":{"@type":"Answer","text":"Voice replication requires consent verification: users must submit a verbal consent recording from the voice owner matching the reference speaker before a voice can be created. Every generated audio clip is also watermarked with SynthID, an imperceptible marker woven into the output, plus C2PA credentials, to keep AI-generated speech detectable and protect voice talent from unauthorized use. Developers building voice-cloning features can weigh consent and watermarking requirements discussed on daily.dev."}}]} ```