Use the correct VAD service

Signed-off-by: Michael Yuan <[email protected]>

Author: juntao

config.toml

@@ -23,14 +23,14 @@ speaker = "speaker2"
 # lang = "zh"
 # api_key = "gsk_xxx"
 # model = "whisper-large-v3-turbo"
+# vad_url = "http://localhost:9093/v1/audio/vad"
 # vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [asr]
 url = "https://whisper.gaia.domains/v1/audio/transcriptions"
 lang = "auto"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
-# vad_url = "http://localhost:9093/v1/audio/vad"
-vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
+vad_url = "http://localhost:9093/v1/audio/vad"
 
 # [llm]
 # llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"

docker/server-vad/config.toml

@@ -15,7 +15,8 @@ lang = "en"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
 # Requires a local Silero VAD server: https://github.com/second-state/silero_vad_server
 # Default port is 8000, but some setups may use 9093. Update the port below if needed.
-vad_realtime_url = "ws://localhost:8000/v1/audio/realtime_vad"
+vad_url = "http://localhost:8000/v1/audio/vad"
+# vad_realtime_url = "ws://localhost:8000/v1/audio/realtime_vad"
 
 [llm]
 llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"

examples/gaia/config.toml

@@ -12,7 +12,8 @@ speaker = "cooper"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # Requires a local Silero VAD server at port 9093: https://github.com/second-state/silero_vad_server
-vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
+vad_url = "http://localhost:9093/v1/audio/vad"
+# vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 # Requires a local LlamaEdge API server at port 9091: https://llamaedge.com/docs/ai-models/llm/quick-start-llm
 [llm]

examples/groq/config.toml

@@ -14,7 +14,8 @@ model = "whisper-large-v3"
 lang = "en"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
 # Requires a local Silero VAD server: https://github.com/second-state/silero_vad_server
-vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
+vad_url = "http://localhost:9093/v1/audio/vad"
+# vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [llm]
 llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"

examples/mcp/config.toml

@@ -15,7 +15,8 @@ model = "whisper-large-v3"
 lang = "en"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
 # Requires a local Silero VAD server at port 9093: https://github.com/second-state/silero_vad_server
-vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
+vad_url = "http://localhost:9093/v1/audio/vad"
+# vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 # Use Groq for fast LLM here
 [llm]