Left is faster. Higher reads more hard parts right.
Gemini 3.8 Flash is better on non-streaming latency, accuracy and naturalness. Qwen3-TTS is better on price.
Last updated Methodology by Dileep Chagam
Measure by measure, the same sentences, the same place.
An estimate: speech-to-text transcribers scored it, not people.
The same sentence, read by each voice.
Gemini 3.8 Flash. Gemini 3.8 Flash: 1.29 s. Qwen3-TTS: 1.65 s.
Gemini 3.8 Flash. Gemini 3.8 Flash: 1.29 s. Qwen3-TTS: 1.65 s.
Neither has a figure. Gemini 3.8 Flash: Can't stream. Qwen3-TTS: Can't stream.
Neither has a figure. Gemini 3.8 Flash: No stop message. Qwen3-TTS: No stop message.
Gemini 3.8 Flash. Gemini 3.8 Flash: 87.7%. Qwen3-TTS: 71.0%.
Qwen3-TTS. Gemini 3.8 Flash: $28.66. Qwen3-TTS: $20.00.