InjazAI

Google released two text-to-speech models, gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts, offering a library of over 2,000 voices and custom voice creation from a 30-second audio sample, cutting synthetic speech costs to a few cents per minute.

1 min read

Google Launches Gemini 3.8 Flash TTS With 2,000+ Voices and 30-Second Voice Cloning

What was released

FAQ

What is Gemini 3.8 Flash TTS?

It is Google's text-to-speech model, released in two versions: gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. It offers a library of over 2,000 voices plus custom voice creation from a 30-second sample.

How does Flash TTS differ from Flash-Lite TTS?

According to the source, Flash-Lite is cheaper than Flash TTS, while Flash TTS was used in the demo to generate 78 seconds of audio for 2.74 cents. The source did not publish a detailed quality comparison between the two.

Can MENA teams use it for Arabic content?

The source does not detail Arabic dialect quality, so teams should test the model on Arabic text before production use. The documented strengths are voice variety and multi-character conversation support.

What is required to create a custom voice?

Per the source, a 30-second audio sample of a voice you have the rights to use is enough.

Source: Simon Willison (LLM & tools)

AI-assisted summary of the source above. High-confidence stories publish automatically; others wait for review. Facts that are not in the source are not added.