Scaling FlashSpeech Parameters and Its Effects on Zero-Shot TTS Latency and MOS Scores

This report synthesises findings from 3 peer-reviewed papers addressing the following research question: How does scaling FlashSpeech from 10M to 1B parameters impact the trade-off between inference latency and MOS scores in zero-shot text-to-speech benchmarks. 6 claims were extracted from source literature; 6 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 7.5/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research goal: How does scaling FlashSpeech from 10M to 1B parameters impact the trade-off between inference latency and MOS scores in zero-shot text-to-speech benchmarks?

Autonomous literature synthesis. Automated review score: 7.5/10. Full text and citation available at Assignee Research.