Codesota · Benchmark · TTS IntelligibilityHome/Leaderboards/Audio & Speech/Text-to-Speech/TTS Intelligibility
Unknown

TTS Intelligibility.

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.

Paper Lineage
§ 01 · SOTA history

Year over year.

Not enough data to show trend.
§ 02 · Leaderboard

Results by metric.

No results yet on this benchmark
Help build the community leaderboard — submit your model results.

No benchmark results available yet for TTS Intelligibility.

Check back soon as we continue collecting data.

Lineage

TTS Intelligibility in context.

See full text-to-speech benchmarks lineage →
Predecessors (1)
saturating2026-04
CodeSOTA TTS Eval
Clean Harvard sentences are not enough for production. The successor benchmark focuses on hard English prompts, critical entity preservation, latency, and cost.
This benchmark (1)
active2026-04
TTS Intelligibility
None yet — this is the current frontier.
§ 04 · Submit a result

Add to the leaderboard.

← Back to Text-to-Speech