ajaysi 746a5eeeb9 Fix LLM provider selection in podcast handlers ...

- Remove hardcoded preferred_provider=huggingface in podcast handlers
- Set preferred_provider=None to respect GPT_PROVIDER env var
- Change default model from Qwen to gpt-oss-120b:cerebras (the model user had access to)
- WaveSpeed will now use gpt-oss-120b model instead of Qwen

2026-04-01 06:54:37 +05:30

..

handlers

Fix LLM provider selection in podcast handlers

2026-04-01 06:54:37 +05:30

constants.py

Refactor podcast media storage to lazy tenant resolver

2026-03-12 14:59:03 +05:30

models.py

feat: Add Auto-Dubbing feature for Podcast Maker

2026-03-24 15:45:51 +05:30

presenter_personas.py

AI podcast project

2025-12-16 16:25:52 +05:30

router.py

Restrict podcast task status access by owner

2026-03-30 08:05:44 +05:30

utils.py

Refactor podcast media storage to lazy tenant resolver

2026-03-12 14:59:03 +05:30