DRAMA-Eval - Script Fidelity WER (English): leaderboard
Speech generators voice whole multi-speaker scenes from structured English scripts built from real podcasts, films and TV series (a set of 501 cases, each turn with delivery directions; systems were scored on up to that many); the score is the word error rate of an ASR transcript of the generated audio against the script. Unlike Seed-TTS-Eval's read-aloud sentences, the text is multi-turn dialogue voiced as one scene.
Metric: Word error rate (%) of Qwen3-0.6B-ASR transcripts of each generated scene against its script, English set (501 cases). Source: aslp-lab.github.io. Saturation forecast: Rough model projection: around 2026. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | FireRedTTS3 | 3.97 | |
| 2 | Ming-3.0-tts-0.5B | 4.13 | |
| 3 | Qwen3-TTS-12Hz-1.7B-VoiceDesign | 4.16 | |
| 4 | SeedAudio 1.0 | 4.45 | |
| 5 | MOSS-TTS-2.0 Preview | 4.87 | |
| 6 | StepAudio 3 Gen | 6 | |
| 7 | FireRedTTS2 | 6.12 | |
| 8 | Ming-3.0-tts-tiny | 7.64 | |
| 9 | Qwen-Audio-3.1-TTS-Next | 7.78 | |
| 10 | Higgs Audio V2 | 8.05 |
Interactive version: theaggregate.ai/benchmark?slug=drama-eval-script-fidelity-wer-english · How It Works · Data refreshed daily, snapshot 2026-11-13.