litellm/litellm/realtime_api
2026-09-02 11:05:38 -07:00
..
main.py fix(azure_ai): route audio and realtime calls on Foundry hosts through the Azure OpenAI handlers 2026-09-02 11:05:38 -07:00
README.md feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00

Abstraction / Routing logic for OpenAI's /v1/realtime endpoints.

Supported endpoints:

  • WebSocket: /v1/realtime (with intent=transcription for transcription-only sessions)
  • HTTP: /v1/realtime/client_secrets, /v1/realtime/transcription_sessions

Supported providers: OpenAI, Azure OpenAI, Bedrock, Vertex AI, xAI.

For user-facing documentation and usage examples, see the litellm-docs repo.