Gemini 3.1 Flash TTS Preview API
About
Build advanced reasoning agents with Gemini 3.1 Flash TTS Preview, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $1.00/1M input and $20.00/1M output tokens. Access Gemini 3.1 Flash TTS Preview via the Google API with up to 16K output tokens.
Capabilities
Input Modalities
text
Output Modalities
audio
Reasoning
Yes
Structured Output
No
Tool Use
No
WeightsClosed
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
8K
Tokens
Input Limit
8K
Tokens
Max Output
16K
Tokens
Pricing
Standard (per 1M tokens)
Input
$1.00
Output
$20.00
Frequently Asked Questions
Gemini 3.1 Flash TTS Preview by Google costs $1.00 per 1M input tokens and $20.00 per 1M output tokens.
Model Details
ID
gemini-3.1-flash-tts-preview
Provider
GoogleFamily
gemini-flash
Release Date
Apr 15, 2026
Knowledge Cutoff
Jan 1, 2025
API Integration
NPM Package
@ai-sdk/google
Environment Variables
GOOGLE_API_KEY
GOOGLE_GENERATIVE_AI_API_KEY
GEMINI_API_KEY