Gemini 3.8 Text-to-Speech: What Do the New Models Offer?

Gemini 3.8 text-to-speech is Google's speech generation system, introduced on September 23, 2026. It comes in two versions: Flash TTS and Flash-Lite TTS. For businesses, it lowers costs while improving quality in voice assistants, voiceover work, and customer experience projects.

In short:

• Two models: Flash TTS (high quality) and Flash-Lite TTS (high volume, low cost)
• Support for over 100 languages, more than 2,000 ready-made voices, custom voice design
• Price dropped to $9 per million tokens, about 55 percent cheaper than the previous model
• Accessible via Google AI Studio and the Gemini API, includes a SynthID watermark

What is Gemini 3.8 text-to-speech?

This system is Google DeepMind's next-generation series of speech generation models. It converts text into natural, human-like speech. The model family consists of two products: Flash TTS and Flash-Lite TTS (DeepMind).

These models make it possible to design voices using natural language. Line-by-line performance direction lets you control the tone, pace, and emotion of speech. They also support more than 100 languages.

For Turkish-speaking businesses, this makes it easier to build multilingual voice products. You can address different markets with a single model.

What's the difference between Flash TTS and Flash-Lite TTS?

The Flash version is designed for custom voice design and high-quality output. It can create a brand-new voice from scratch or clone an existing voice from just a 30-second audio sample (DeepMind).

Flash-Lite TTS serves a different purpose. It focuses on high-volume, cost-efficient production scenarios. It's suited for voice agents, automated read-aloud features, and bulk content generation.

In short, Flash is built for studio-quality work, while Flash-Lite is built for operations at scale. Businesses can choose between the two based on their needs.

How has pricing changed?

This model family has become noticeably cheaper compared to the previous version. The new price stands at $9 per million tokens, effective as of late 2026 (OrcaRouter).

The previous Gemini 3.1 Flash TTS Preview model cost $20 per million audio tokens. That amounts to roughly a 55 percent price drop.

title: TTS Price (per million tokens, $)
source: OrcaRouter | https://www.orcarouter.ai/blog/gemini-3-8-tts-says-hello
Gemini 3.8 Flash TTS*: 9
Gemini 3.1 Flash TTS Preview: 20

Audio is calculated at roughly 25 tokens per second. That translates to a cost of about 0.02 cents per second. For businesses producing high volumes of voice content, this difference offers a meaningful budget advantage.

Does it stand out in quality compared to competitors?

These models performed well in an independent quality test. On the Hume AI Voice Design Benchmark, Flash TTS ranked first in the overall category with a score of 71.4 (DeepMind).

title: Hume AI Voice Design Benchmark
source: DeepMind | https://deepmind.google/blog/say-hello-to-gemini-38-text-to-speech
Gemini 3.8 Flash TTS* (overall): 71.4
Gemini 3.8 Flash TTS* (accent): 60.8
max: 100

It also leads in the accent modeling category with a score of 60.8. These results show that the model produces not just fast but also high-quality audio. This is a significant advantage for projects that require precision in accent and intonation.

What are the standout features?

This system allows for adding realistic conversational textures. Thanks to a backchanneling feature, you can insert natural vocal reactions like "|mhm|" or "|yeah|" (DeepMind).

Controllability is another standout aspect. Style, accent, pace, and tone can be directed using structured speech_metadata descriptions and inline speech tags (Google AI Developers).

Below are the notable technical limits and features:

The multi-speaker configuration currently supports only two speakers (Firebase). The maximum output length is approximately 655 seconds; text exceeding this limit gets cut off (Google Cloud).

How is security and verification handled?

This model family includes additional safeguards around voice identity verification. The models come with built-in consent verification, which makes unauthorized voice cloning harder to do.

It also uses C2PA credentials and a SynthID watermark (DeepMind). These two technologies help verify that the generated audio was created by AI.

For businesses, this matters both for legal compliance and user trust. It builds a layer of defense against fake audio content.

Where can you access it?

These models are available through Google AI Studio and the Gemini API. Developers can use these tools to add speech generation to their existing applications.

For teams building voice assistants, e-learning platforms, or customer service bots, integration is relatively quick. Similarly, anyone curious about the price-performance balance across AI models can also check out our Claude Opus 5.5 analysis.

Frequently asked questions

How much cheaper is Gemini 3.8 TTS compared to previous models?

The new price is $9 per million tokens, compared to $20 for the previous Gemini 3.1 Flash TTS Preview. That's roughly a 55 percent drop.

Should I choose Flash or Flash-Lite?

Flash is suited for studio work that requires custom voice design and high quality. Flash-Lite is designed for high-volume, cost-efficient production scenarios.

How do you create a custom voice?

You can create a brand-new voice from scratch using natural language instructions. Alternatively, you can clone an existing voice using just a 30-second audio sample.

Which languages does it support?

The system supports more than 100 languages, including regional accents. It also offers more than 2,000 ready-made voice options.

With its lower price and advanced control options, this model family offers a practical choice for voice products. If you want to design the right voice experience for your business, you can discuss integrations like these with the EngerekTech team.

Sources