Fix STT: AWS Transcribe takes priority over LiteLLM in auto-detect
LiteLLM's atranscription has a routing bug with Vertex AI Chirp proxy. AWS Transcribe is already configured and working. Auto-detect now prefers AWS over LiteLLM. Use TRANSCRIBE_PROVIDER=litellm to force LiteLLM.
This commit is contained in:
parent
63d8a881cb
commit
7a50bc061d
1 changed files with 3 additions and 2 deletions
|
|
@ -22,9 +22,10 @@ function getTranscribeProvider() {
|
|||
if (env === 'local') return 'local';
|
||||
if (env === 'aws') return 'aws';
|
||||
if (env === 'openai') return 'openai';
|
||||
// Auto-detect: use LiteLLM when configured (it handles audio transcriptions)
|
||||
if (process.env.LITELLM_API_BASE && litellmClient) return 'litellm';
|
||||
// Auto-detect priority: AWS > LiteLLM > OpenAI
|
||||
// LiteLLM's Vertex AI audio proxy has routing bugs — only use it if explicitly set
|
||||
if (isAWSTranscribeConfigured()) return 'aws';
|
||||
if (process.env.LITELLM_API_BASE && litellmClient) return 'litellm';
|
||||
return 'openai';
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Reference in a new issue