Gemini 3.8 Flash-Lite TTS
google / gemini-3-8-flash-lite-tts

Google’s efficient text-to-speech model built for low-latency, high-throughput voice generation. Gemini 3.8 Flash-Lite TTS supports natural speech across 101 languages, voice replication, multi-speaker audio, and long-form generation, making it ideal for voice agents and high-volume TTS workflows.

Pricing: Input 70 credits / 1M tokens (≈ $0.35), Audio Output 840 credits / 1M tokens (≈ $4.20) — both 30% below official pricing. Limited-Time Offer: these prices follow Google's promotional pricing and are valid until Dec 31, 2026. High-tier top-ups come with bonus credits that lower the effective price by about 10%.
Input
0 / 2
No items yet. Click Add to start.

At least 1 item(s) required

0
No items yet. Click Add to start.

At least 1 item(s) required

When true, filler words like "hmm" and "ahh," interjections, and natural background sounds will be added to the conversation.

Controls the randomness of the speech output. Higher values produce more creative and varied delivery, while lower values make the output more predictable and focused. Default value: 1

Output
output typeaudio

README

Complete guide to using google/gemini-3-8-flash-lite-tts

Gemini 3.8 Flash-Lite TTS API – Try Google Gemini 3.8 TTS More Efficiently

Original image
Generate Speech with Low-Latency Gemini 3.8 Flash-Lite TTS
Scale High-Volume TTS with Better Cost Efficiency
Clone Voices from 30s Audio with Google Gemini 3.8 Flash-Lite TTS
Create Natural Multi-Speaker Conversations
Generate Long-Form Audio with Gemini 3.8 Text-to-Speech
Generate Speech in 101 Languages with Gemini 3.8 Flash-Lite TTS
Gemini 3.8 Flash-Lite TTS vs Flash TTS: What’s the Difference?
Access Both Gemini 3.8 TTS APIs on Kie AI

Gemini 3.8 Flash-Lite TTS is Google’s fast, cost-efficient text-to-speech model designed for high-throughput production. It generates natural speech while prioritizing low latency and scalability for voice agents, read-aloud features, bulk audio, and everyday TTS applications.

The Gemini 3.8 Flash-Lite TTS API is best suited for applications that need fast and scalable speech generation. Common use cases include AI voice agents, read-aloud tools, high-volume audio production, SaaS voice features, and automated text-to-speech workflows.

Yes. Gemini 3.8 Flash-Lite TTS supports Voice Replication, allowing developers to recreate vocal characteristics from authorized reference audio and use the replicated voice for new speech generation.

Gemini 3.8 Flash-Lite TTS supports 101 languages and automatically detects the input language. This makes it suitable for multilingual voice agents, localized applications, read-aloud features, and global text-to-speech products.

Gemini 3.8 Flash-Lite TTS prioritizes high throughput, low latency, and cost efficiency, while Gemini 3.8 Flash TTS focuses more on maximum voice fidelity, acting nuance, and dialect coverage. Flash-Lite supports 101 languages, while Flash supports 130.

Yes. You can try Gemini 3.8 Flash-Lite TTS free on Kie AI with available credits. Generate sample speech online to evaluate the model before integrating the API into your application.

Start by testing Gemini 3.8 Flash-Lite TTS on Kie AI, then get your Kie AI API credentials and connect the model to your application. You can use the API for SaaS products, voice agents, read-aloud tools, and automated speech-generation workflows.