Definitions for every metric reported on the Performance page. Grouped by category.
Naturalness — higher is better
- Overall — Holistic listener rating of how natural the voice sounds end-to-end.
- Naturalness — How human-like the voice sounds; penalizes robotic or synthetic quality.
- Intonation — Whether pitch rises and falls appropriately for the sentence type (question, statement, exclamation).
- Prosody — The broader umbrella of rhythm, stress, and melody, how well the voice “reads” the sentence as a human would.
- Pronunciation — Whether individual words are phonetically correct, especially names, loanwords, and domain-specific terms.
- Audio Quality — Technical cleanliness of the output; absence of artifacts, distortion, clipping, or background noise.
Expressiveness — higher is better
- Overall — Holistic listener rating of how expressive the voice sounds given the context of the sentence.
- Paralinguistics — Non-verbal vocal elements like laughter, sighs, or filler sounds (“um”, “uh”) and whether they’re rendered appropriately.
- Emotions — How accurately the voice conveys the intended emotional tone (neutral, warm, urgent, etc.).
Delivery — higher is better
- Boundary Consistency — Whether phrase and sentence boundaries are marked consistently with pauses or pitch shifts, without arbitrary breaks mid-phrase.
- Pronunciation Style — Not just correctness, but stylistic choices i.e., formal vs. casual register, regional accent consistency, honorific handling.
- Natural Pace — Whether the speaking rate feels comfortable and appropriate for the content type, neither rushed nor dragging.
- Pause Placement — Whether silences appear at semantically correct points (after commas, between clauses) rather than mid-word or mid-phrase.
- Breathing Naturalness — Whether breath sounds occur at realistic points and with realistic frequency, not absent entirely or inserted randomly.
Accuracy
Mixed direction — WER, CER, Hallucination, and Deletion are lower is better; Pronunciation % is higher is better.
- WER (Word Error Rate) — Percentage of words in the transcript that differ from the reference; measures how faithfully the TTS renders the input text.
- CER (Character Error Rate) — Like WER but at the character level.
- Hallucination — Words or sounds the TTS generates that have no basis in the input text. Insertions, substitutions, or fabricated content.
- Deletion — Words from the reference text that the TTS dropped entirely.
- Pronunciation % — The proportion of words pronounced correctly out of total words.
- Whisper jiwer vs Whisper LLM — Two judging methodologies.
jiwer uses raw Whisper-decoded transcripts; LLM-judged uses a follow-on LLM to normalize transcription noise. Both report the same metric family; LLM-judged tends to give lower error rates by reducing false positives from punctuation/casing.
MOS v2 — higher is better
- Mean MOS — Mean Opinion Score: average listener rating on a 1–5 scale across the test set; the canonical aggregate quality metric in TTS evaluation.
- UTMOS — A predicted MOS from the UTMOS reference model — an automated proxy for subjective quality.
- WV-MOS — A predicted MOS from the WavLM-based WV-MOS reference model — another automated proxy commonly reported alongside UTMOS for cross-validation.
Latency
- TTFB (Time-to-First-Byte) — Wall-clock delay between sending the synthesis request and the first audio byte arriving on the wire. Lower is better for real-time and conversational use cases.
- Real-Time Factor (RTF) —
RTF = Audio Duration ÷ Processing Time. Values above 1.0 mean the model produces audio faster than playback.
Next Steps
- Performance — head-to-head benchmark tables across all metrics above.
- TTS Evaluation Script — Python script to measure TTFB in your own environment.
- Lightning v3.1 model card — full Standard catalog + capabilities.
- Lightning v3.1 Pro model card — full Pro catalog + capabilities.
