support TTS /v1/audio/speech (#36)

README.md

@@ -21,7 +21,12 @@ Any OpenAI compatible server would work. llama-swap was originally designed for
 - ✅ Easy to config: single yaml file
 - ✅ On-demand model switching
 - ✅ Full control over server settings per model
-- ✅ OpenAI API support (`v1/completions`, `v1/chat/completions`, `v1/embeddings` and `v1/rerank`)
+- ✅ OpenAI API supported endpoints:
+  - `v1/completions`
+  - `v1/chat/completions`
+  - `v1/embeddings`
+  - `v1/rerank`
+  - `v1/audio/speech`
 - ✅ Multiple GPU support
 - ✅ Run multiple models at once with `profiles`
 - ✅ Remote log monitoring at `/log`

proxy/proxymanager.go

@@ -78,6 +78,9 @@ func New(config *Config) *ProxyManager {
 	pm.ginEngine.POST("/v1/embeddings", pm.proxyOAIHandler)
 	pm.ginEngine.POST("/v1/rerank", pm.proxyOAIHandler)
 
+	// Support audio/speech endpoint
+	pm.ginEngine.POST("/v1/audio/speech", pm.proxyOAIHandler)
+
 	pm.ginEngine.GET("/v1/models", pm.listModelsHandler)
 
 	// in proxymanager_loghandlers.go