Not published
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
MODEL REFERENCE / GOOGLE
Google's production text-to-speech model optimized for high-throughput, low-latency and cost-efficient speech generation.
PRIMARY-SOURCE VERIFIED
Google documents a 8,192-token context window. Input modalities: text. Output: audio. Pricing status: Official paid API.
CAPABILITY CONTRACT
Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.
Input modalities come from the cited official model documentation.
Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.
PRICING STATUS
$0.50 input · $0.125 cached · $6.00 output per 1 million tokens.
SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.
CAVEATS
Google lists Gemini 3.8 Flash-Lite TTS as generally available as of September 22, 2026 and as the production replacement for gemini-3.1-flash-tts-preview.
Standard pricing uses text input tokens and audio output tokens; audio output tokens correspond to 25 tokens per second.
The model is excluded from the generic generative token calculator because its output-token dimension represents audio rather than text.
EXPLORE
OFFICIAL SOURCES
WHAT CHANGED
No post-baseline factual changes recorded for Gemini 3.8 Flash-Lite TTS since 2026-10-06.
VERIFIED CHANGE HISTORY
Baseline verified: 8,192 context · 16,384 max output · $1.00 input / $0.25 cached / $12.00 output per 1 million tokens
Official evidence ↗Append-only SXF ledger · 1 verified event · chain head a81376cb9fe2…