Google
The latest voice foundation model from Google DeepMind, integrating extended chain-of-thought reasoning directly into live spoken dialogues.
262.144K ctx$0.0035 / min (Live Extended Thinking)
Introducing Gemini 3.1 Flash Audio (Flash Live, TTS)GoogleReleased April 15, 2026
Gemini 3.1 Flash Audio (Flash Live, TTS)
Dedicated conversational voice model providing native bidirectional speech streaming with 220ms end-to-end latency.
multimodal-realtimeProprietary API$0.003 / min audio (Live)Context: 131.072K (131,072 tokens)
Technical Specifications
Architecture Type
Native Speech-to-Speech Transformer
Total Parameters
Undisclosed
Context Window
131.072K (131,072 tokens)
Max Output Tokens
8.192K (8,192 tokens)
Knowledge Cutoff
December 2025
Supported Modalities
audio, text, speech
License & Access
Google Cloud API Terms of Service
Benchmark Evaluations
Speech Wer
4.1
Audio Latency Ms
220
Emotion Fidelity
94.2
Deep Architectural Overview
Gemini 3.1 Flash Audio eliminates traditional text-to-speech transcoding pipelines. By processing and synthesizing acoustic tokens natively, it conveys subtle emotional inflection, natural pauses, and human-like interruption handling.
Strengths & Considerations
Core Strengths
- 220ms glass-to-glass audio latency
- Native emotional prosody and accent synthesis
- Seamless interruption handling
Known Limitations
- Context limited to 128k audio tokens
Token & API Pricing
Input Tokens (1M)$0.25
Output Tokens (1M)$1.00
Cached Input (1M)$0.0625
Pricing is verified directly against Google's developer documentation and API rate sheets.
Similar & Alternative Models
Explore other frontier models from Google and comparable reasoning engines.
Google
The latest evolution in the Gemini 3 family, delivering state-of-the-art software engineering (73.7% DeepSWE) and agentic enterprise knowledge workflows.
1.049M ctx$0.75 / 1M tok ($1.50 reg)
Google
Universal omnimodal generation model that accepts any combination of text, audio, image, and video to generate any combination of outputs.
1.049M ctx$0.60 / 1M tok (Universal Omni)
Google
Universal multilingual speech engine supporting live simultaneous translation and speaker diarization across 100+ languages.
262.144K ctx$0.0025 / min audio (Translate & Live)