CodeSOTA benchmark for production TTS information preservation. English prompts are synthesized by each TTS provider, transcribed by an independent ASR, then compared against the reference text with WER, CER, exact match, critical entity accuracy, severity-weighted error taxonomy, latency, and cost columns. Designed for speed vs quality vs cost comparisons in voice-agent workflows.
No benchmark results available yet for TTS Intelligibility.
Check back soon as we continue collecting data.