Skip to content

Comparison · read on October 27, 2026

Gradium TTS vs Inworld Realtime TTS-2 Flash

Two text-to-speech (TTS) models side by side, from four public benchmarks. Speed comes first, then listener rating and price; the three are never added into a score.

MeasureGradium TTSInworld Realtime TTS-2 Flash
ProviderGradiumInworld
Speed tierHeadroomHeadroom
P95 time to first audio104.3 ms100.9 ms
Median time to first audio53.7 ms58.1 ms
Listener Elo1,1741,218
Price per 1M characters$36 to $57.8$10.4 to $15
AccessProprietaryProprietary
Rank in the full ranking23
Rank by use caseCustomer service 1, Voice agents 2, Assistants 1, Entertainment 1, Knowledge sharing 1Customer service 2, Voice agents 3, Assistants 2, Entertainment 2, Knowledge sharing 2

Which should you choose?

Where a model is not timed or not rated, nothing is estimated. See each model page for its sources: Gradium TTS and Inworld Realtime TTS-2 Flash.

Frequently asked questions

Which is faster, Gradium TTS or Inworld Realtime TTS-2 Flash?
Speed: Gradium TTS and Inworld Realtime TTS-2 Flash are a tie (104.3 ms against 100.9 ms at P95).
Which is rated higher by listeners, Gradium TTS or Inworld Realtime TTS-2 Flash?
Listener rating: Inworld Realtime TTS-2 Flash comes out ahead (Elo 1,174 against 1,218; scores within each other's 95% intervals are a tie).
Which is cheaper, Gradium TTS or Inworld Realtime TTS-2 Flash?
Price: Inworld Realtime TTS-2 Flash comes out ahead ($36 to $57.8 against $10.4 to $15 per million characters, lowest list price).
Why is this model always on the left?
Gradium TTS is the reference model of this site's comparison pages: it is set against every other listed model. The editor chose it; it is not chosen by rank.