Simon Willison's Weblog ·
Simon Willison describes Google’s release of gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. He writes that the models offer over 2,000 voices and custom voices from a 30-second sample of a voice the user owns or has rights to use, and describes defining conversations with different voices and voice style instructions. Read 3 viewpoints with supporting evidence and source links.
Lines show the reading structure. Select an idea to read its explanation and evidence.
Synthesis
Google released two new Gemini text-to-speech models: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts.
Original excerpt
Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts .
Simon Willison · Paragraph 1
Read in source context →Continue exploring
AI model release →The Gemini TTS models support custom voice creation using just a 30-second audio sample of a voice the user owns or has rights to use.
Original excerpt
They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use".
Simon Willison · Paragraph 2
Read in source context →Continue exploring
voice customization →The Gemini TTS API enables defining full conversations between multiple characters, each assigned a distinct voice and voice style instructions.
Original excerpt
A notable feature of the API is that it makes it easy to define a full conversation between multiple characters, each with different voices and voice style instructions.
Simon Willison · Paragraph 4
Read in source context →Continue exploring
multi-character TTS →Attributed passages with the context to verify them. Open the original text to check the source.
Original excerpt
A notable feature of the API is that it makes it easy to define a full conversation between multiple characters, each with different voices and voice style instructions.
Original excerpt
They come with a library of over 2,000 voices, plus the ability to create a custom voice with "just a 30-second audio sample of your voice or a voice you have the rights to use".
Original excerpt
Google released two new Gemini text-to-speech models today - gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts .
Google released the gemini-3.8-flash-lite-tts model as one of two new Gemini text-to-speech models.
Read supporting evidence · Simon WillisonGoogle released the gemini-3.8-flash-tts model as one of two new Gemini text-to-speech models.
Read supporting evidence · Simon WillisonThese viewpoints are linked to their original sources. Paraphrases are labeled and are not verbatim quotes.
Open transcript or source material (opens in a new tab)Report an issueSimon Willison on AI model capability comparison, AI model performance and cost, AI model release. Explore 15 viewpoints by topic, with evidence from 5 sources.
