scribe

4 Commits

Include renames

Author	SHA1	Message	Date
admin	42afe111bd	Remove language and num_speakers from MCP server Mirror and run GitLab CI / build (push) Has been cancelled Details Ruff / ruff (push) Has been cancelled Details - TranscribeRequest now only accepts audio_base64, audio_url, or audio_path. - Hard-code language and num_speakers to None in transcription calls.	2026-06-20 01:23:40 +00:00
admin	332c88f99d	Update MCP server to expose clear JSON tool schema Mirror and run GitLab CI / build (push) Has been cancelled Details Ruff / ruff (push) Has been cancelled Details - Use Pydantic models and explicit operation_ids. - No multipart; accept audio_base64, audio_url, or audio_path via JSON. - Ensure OpenAPI spec is fully self-describing for MCP tool generation.	2026-06-20 01:19:35 +00:00
admin	099fb30e6c	Update MCP server to accept JSON body with audio_base64/audio_url Mirror and run GitLab CI / build (push) Has been cancelled Details Ruff / ruff (push) Has been cancelled Details - Remove multipart form; use JSON with audio_base64 or audio_url. - Add internal audio_path field for internal use. - Keep OpenAPI spec consistent with new schema.	2026-06-20 01:15:50 +00:00
admin	54414def26	Add MCP-style API server (OpenAPI) alongside WebUI Mirror and run GitLab CI / build (push) Has been cancelled Details Ruff / ruff (push) Has been cancelled Details - New mcp_server.py: FastAPI app for LLMs to upload audio and get transcript JSON. - Added process_mcp_transcribe_task Celery task. - Updated __main__.py: WebUI always runs; MCP server runs in parallel when MCP_SERVER_ENABLED=true.	2026-06-19 17:04:44 +00:00