Last refresh: Aug 19, 2026
texttospeech.com Get the data

Sources & snapshots

Get the text-to-speech benchmark data

Every ranking this site has ever shown is an immutable snapshot: the raw board scores, the alias mappings that were applied, and the rules the composite was computed with. Download any of them as JSON — re-running the published formula over a snapshot reproduces the exact board it rendered.

The boards

BoardSignalStatus
artificialanalysis.com Speech Arena Elo live
voicearena.com arena Elo, US English live
humannessindex.vapi.ai humanness score 0–100 live

Snapshot archive

SnapshotModelsDownload
2026-08-19T14-05-26Z · current 108 models · captured Aug 19, 2026 JSON (download)
2026-08-19T04-01-20Z 103 models · captured Aug 19, 2026 JSON (download)
2026-08-17T04-00-44Z 103 models · captured Aug 17, 2026 JSON (download)
2026-08-15T18-49-58Z 103 models · captured Aug 15, 2026 JSON (download)
2026-08-14T10-43-32Z 99 models · captured Aug 14, 2026 JSON (download)

Snapshots are append-only. Each file contains boards (source list, status, normalization strategy, board size), models (raw scores per board, aliases applied, metadata), and rules (the scoring mode, board authorities, and the dataset constants the score was computed with). Ranks and the BPRA score are recomputed from these values — nothing pre-baked, nothing editable after the fact.