scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 178
litellm/litellm/realtime_api
History
mateo-berri e56c42862c fix(health): probe Azure GA realtime path for transcription-only models 
The realtime health check always built the Azure websocket URL with the
default beta protocol, so GA-only transcription models such as
azure/gpt-realtime-whisper got probed at /openai/realtime and were
rejected with HTTP 400 on every /health run, while real calls through
the proxy resolved the GA path via intent=transcription and worked.

The probe now resolves the protocol the way the real call path does:
an explicit realtime_protocol (argument, deployment litellm_params, or
LITELLM_AZURE_REALTIME_PROTOCOL) wins, transcription-only models fall
back to GA with intent=transcription, and everything else keeps beta.
Transcription-only detection reads both mode and supported_endpoints
from get_model_info because a live proxy overwrites the catalog mode
with the operator's deployment model_info (mode: realtime) during
router registration, while supported_endpoints survives it.
get_model_info now propagates supported_endpoints from the cost map;
it declared the field but never populated it.
2026-08-26 12:14:52 -07:00
..
main.py fix(health): probe Azure GA realtime path for transcription-only models 2026-08-26 12:14:52 -07:00
README.md feat: litellm oss 110626 (#30202) 2026-06-11 22:30:26 -07:00

README.md

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.