2026.09.22
BetaUnverifiedAdded Sep 25, 2026
Our new Text-to-Speech model is available in public beta, with lower latency and more expressive speech. In our latest measurements, the beta reaches time to first audio in under 50 ms, against 225 ms for the production model. Latency varies with network conditions and input. Set model_name to "gradium-tts-beta" in your TTS setup to use the beta.
Topics: Developer tools, Performance
More releases
Every release| Date | Release | Type |
|---|---|---|
| Aug 16 | 2026.09.24unverified Beta | Beta |
| Aug 16 | 2026.09.16unverified Update | Update |
| Aug 16 | 2026.08.24unverified Update | Update |
| Aug 16 | 2026.08.10unverified Beta | Beta |
| Aug 16 | 2026.07.28unverified Update | Update |
| Aug 16 | 2026.07.22unverified Update | Update |
| Aug 16 | 2026.02unverified Update | Update |
| Sep 25 | 2026.09.15unverified Preview | Preview |
Also shipped on Aug 16, 2026
in August 2026| Date | Company | Release | Product | Type |
|---|---|---|---|---|
| Aug 16 |  Snowflake | Feature policy rules (General availability) | Snowflake | GA |
| Aug 16 |  OpenAI | OpenAI Agents SDK 0.21.1unverified | OpenAI Agents SDK | Update |
Sources: each vendor's own release notes, changelogs and GitHub releases, read daily to monthly by how often it posts. Logos via logo.dev; trademarks belong to their owners.