You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Azure offers a wide range of AI and cloud services that can enhance Moltbot. With PR #3675 adding Azure OpenAI model support, I'd like to discuss a roadmap for comprehensive Azure integration.
I previously submitted PR #3144 which included working implementations of:
Azure OpenAI provider (including GPT-5.2)
Azure Speech TTS
Azure Speech STT
Testing Status
All features have been tested and verified working on version 2026.1.27-beta:
✅ Azure OpenAI GPT-5.2 - Successfully tested and working
✅ Azure Speech TTS - Successfully tested and working
✅ Azure Speech STT - Successfully tested and working
Note: This addresses the question from @Takhoffman on PR #3144 about whether GPT-5.2 was tested - yes, it has been tested successfully.
The PR was closed because the scope was too large (1000+ lines), not due to code quality issues. I understand the concern about reviewing large PRs and am happy to break this into smaller, focused PRs for easier review.
Proposed Approach
Since the code is already implemented and tested, I can:
Extract Azure Speech TTS (~200 lines) - Submit as a small, focused PR
Extract Azure Speech STT (~200 lines) - Submit as a separate small PR
This way, each PR is <300 lines and easy to review, while still delivering the full Azure Speech functionality.
Phase 2: Extended Services (Future consideration)
Azure Translator - Multi-language translation
Azure Content Safety - Content moderation
Azure Communication Services - SMS/Voice calls
Questions for Maintainers
Is comprehensive Azure support a direction the project wants to pursue?
Since the code is already implemented and tested, should I extract TTS and STT into separate small PRs?
Summary
Azure offers a wide range of AI and cloud services that can enhance Moltbot. With PR #3675 adding Azure OpenAI model support, I'd like to discuss a roadmap for comprehensive Azure integration.
Current Status
Background
I previously submitted PR #3144 which included working implementations of:
Testing Status
All features have been tested and verified working on version
2026.1.27-beta:The PR was closed because the scope was too large (1000+ lines), not due to code quality issues. I understand the concern about reviewing large PRs and am happy to break this into smaller, focused PRs for easier review.
Proposed Approach
Since the code is already implemented and tested, I can:
This way, each PR is <300 lines and easy to review, while still delivering the full Azure Speech functionality.
Phase 2: Extended Services (Future consideration)
Questions for Maintainers
Related
Happy to align on the approach. I can have the small PRs ready quickly since the implementation is already done and tested!