7.0.0 (2026-04-27)
6.1.1 (2026-03-27)
6.1.0 (2026-03-26)
- agent: support multi-provider speak/think configuration and typed listen parameters (#676) (5dfb1aa)
6.0.1 (2026-02-24)
6.0.0 (2026-02-23)
- promote v6.0.0-rc.2 to v6.0.0 stable
- promote v6.0.0-rc.2 to v6.0.0 stable (34f543e)
6.0.0-rc.2 (2026-02-18)
- sagemaker: extract SageMaker transport to separate package (#663) (d82b699)
- sagemaker: move SageMaker transport to separate package (#662) (16d500e)
6.0.0-rc.1 (2026-02-16)
- v6 — fully generated SDK with latest APIs and WebSocket support (#640)
- helpers: add TextBuilder class for TTS pronunciation and pause controls (#660) (4324120)
- sagemaker: add SageMaker transport support via the separate
deepgram-sagemakerpackage (pip install deepgram-sagemaker) (#659) - v6 — fully generated SDK with latest APIs and WebSocket support (#640) (bc918fe)
- websockets: add custom WebSocket transport support (#658) (f6cf0fb)
5.3.2 (2026-01-29)
- speak: correct TTS warning event field names to match API response (#653) (f7ab1da)
- types: change speaker and related fields from float to int (#652) (00ee485), closes #641
- websockets: support array parameters in Listen v1 and v2 clients (#650) (38cc1e5)
- release 5.3.2 (d61ce8c)
5.3.0 (2025-10-30)
5.2.0 (2025-10-21)
5.1.0 (2025-10-16)
- mention keep alive in migration guide (#594) (5a8c79e)
- update the SDK with upstream spec changes (d77ad96)
- ci: reference the correct secret (#585) (09550c7)
- corrects order to the release workflow (#583) (3abbac3)
- remove testpypi we don't need it in the workflow (#582) (b2e2538)
- support multiple keyterms for v2 listen client (#595) (7a9d41d)
5.0.0 (2025-10-02)
- This is a significant breaking change, and should be carried out in conjunction with our migration guide.