← Back to Home

Tag: 语音合成 (2 articles)

Engineering TTS Inference in vLLM-Omni

TTS inference is a heterogeneous pipeline combining latency-bound and throughput-bound stages, making traditional LLM optimization strategies ineffective and requiring architecture-aware scheduling.

vLLM Blog · Jun 23, 2026

Gemini 3.1 Flash TTS

Google's Gemini 3.1 Flash TTS is revolutionary because it uses detailed, screenplay-like prompts to precisely control emotion, accent, pace, and scene in speech synthesis, marking a shift from a 'tool' to a 'creative partner'.

Simon Willison · Apr 16, 2026