Breaking Change: GET /v1/models Response Format
UpdateUnverifiedAdded Sep 24, 2026
The self-hosted GET /v1/models endpoint now lists every loaded model, not just core speech-to-text (Nova) models. The response now also includes Text-to-Speech (Aura voice packs and voices) and helper models (entity detection/NER, diarization), groups results by model type, and indicates batch versus streaming mode for each speech-to-text model.
More Deepgram releases
Every Deepgram release| Date | Release | Type |
|---|---|---|
| Jun 30 | Container Images (release 260630)unverified Update | Update |
| Jun 30 | This Release Contains The Following Changesunverified Update | Update |
| Jul 1 | Claude Sonnet 5 Now Availableunverified Update | Update |
| Jul 1 | Deprecation: Claude Sonnet 4unverified Deprecation | Deprecation |
| Jul 2 | 🆕 Word-Level Timestamps Now Available in Fluxunverified Update | Update |
| Jul 2 | SDK Compatibilityunverified Update | Update |
| Jul 2 | Learn Moreunverified Update | Update |
| Jun 24 | 🆕 Redaction: Expanded Language Coverage & Flux Supportunverified Update | Update |
Also shipped on Jun 30, 2026
Deepgram in June 2026
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.