Skip to main content
BenchLM
Official provider results

Gemini 3.8 TTS launch evaluation

Google’s September 23 launch post reports Hume voice-design and quality placements for Gemini 3.8 Flash TTS and Flash-Lite TTS.

Source snapshots refreshed
Five measurement lanesVOICE / S2S

Reasoning, task completion, conversation dynamics, experience, and latency stay separate.

Back to directory

Benchmark profile

Scope
Hume Voice Design Benchmark, accent modeling, and Overall Quality Index, as reported by Google in its launch post
Primary metric
Provider-reported voice quality and design results (higher is better)
Owner
Google DeepMind
Available evidence
Google states the Flash TTS design and accent scores and the two quality-index placements in prose; it does not state Flash-Lite’s underlying quality score.

What it measures

Voice experience
Is the exchange natural, robust, and responsive?

Available results

Gemini 3.8 Flash TTS · Hume Voice Design Benchmark
71.4
#1

Google-reported overall voice-design result.

Gemini 3.8 Flash TTS · Hume accent modeling
60.8
#1

Google-reported accent-modeling result.

Gemini 3.8 Flash TTS · Hume Overall Quality Index
#1
Score not stated

Google reports the placement without an exact quality-index score in the launch prose.

Gemini 3.8 Flash-Lite TTS · Hume Overall Quality Index
#2
Score not stated

Google reports the placement without an exact quality-index score in the launch prose.

Interpretation limit

These are Google-reported placements on third-party Hume evaluations, not independently verified results in this catalog. Flash-Lite has no published exact quality-index value in the launch prose. Voice evaluations remain separate from weighted text-model rankings.