Pending benchmarksTracking since Oct 31, 2026
Is STORM Ensemble 3.0 state of the art?Pending benchmarks.Announced Oct 31, 2026; no independent results yet.
A 3B text-to-speech model from London-based PlotWeaver covering 64 African and Nigerian languages plus English with 166 named voices at 24 kHz, all in one model. PlotWeaver's CEO unveiled it on October 31, 2026. API access is by request through PlotWeaver's developer platform. No open weights.
Announced facts
The details so far
- Lab
- PlotWeaver
- Announced
- Oct 31, 2026
- API
- Waitlist · PlotWeaver developer platform, access by request, usage-based billing. Its docs list TTS models storm-v1, storm-v2 and storm-v3 (73 African languages); which id serves Ensemble 3.0 is not stated
- Open weights
- Closed · Not released
- Languages
- 64 African and Nigerian languages plus English, in one model
- Voices
- 166 named voices; PlotWeaver says it evaluated every language speaker by speaker and left out voices below its bar
- Size
- 3B parameters
- Audio
- 24 kHz output
- Company
- PlotWeaver Limited, London (Companies House no. 16189457)
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Self-reported
What the lab claims
Self-reported. Shown for context; not used in any verdict.
Lab claim: PlotWeaver's CEO calls it the most capable speech model the company has built.
Receipts
Sources
LABSTORM Ensemble (PlotWeaver)plotweaver.app/storm-ensembleLABPlotWeaver CEO unveils STORM Ensemble 3.0 (X)x.com/wolefizzy/status/2116514491038834871 · Oct 31, 2026LABPlotWeaver developer docsdeveloper.plotweaver.app/docsTracking ends Jan 29, 2027 unless the API or weights become available.