From the source
The evaluation of text-to-speech models involves multiple dimensions including correctness, audio quality, naturalness, and robustness, and metrics like word error rate saturate as models improve.
Is this TTS model good?
From the source
This multidimensionality is why TTS evaluation is tricky and as models improve, the evaluation shifts away from obvious defects like mispronounced words, garbled audio, or background noise towards more nuanced aspects.
cartesia.ai
- Announced
- 28 Jul 2026
- First seen by forck
- 03 Sep 2026 14:38 UTC (≥36d after)
