Merge branch 'main' into new-examples

Signed-off-by: Michael Yuan <michael@secondstate.io>

Author: juntao

.github/workflows/release.yml

@@ -89,7 +89,8 @@ jobs:
             build-essential \
             git \
             curl \
-            unzip
+            unzip \
+            cmake
 
       - name: Check out repository
         uses: actions/checkout@v4

Cargo.lock

@@ -1,6 +1,6 @@
 [package]
 name = "echokit_server"
-version = "0.2.0"
+version = "0.2.5"
 edition = "2021"
 
 [dependencies]
@@ -23,8 +23,11 @@ axum-extra = { version = "0.10.0", features = ["typed-header"] }
 tokio = { version = "1", features = ["full"] }
 
 reqwest = { version = "0.12", features = ["multipart", "json", "stream"] }
+
 hound = "3.5.1"
 wav_io = "0.1.15"
+opus = "0.3.0"
+
 rand = "0.9.0"
 uuid = { version = "1.14", features = [
     "v4",       # Lets you generate random UUIDs

Cargo.toml

@@ -27,6 +27,7 @@ speaker = "speaker2"
 # vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [asr]
+platform = "whisper"
 url = "https://whisper.gaia.domains/v1/audio/transcriptions"
 lang = "auto"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
@@ -39,8 +40,9 @@ vad_url = "http://localhost:9093/v1/audio/vad"
 # history = 1
 
 [llm]
-prompts_url = "http://localhost:8001/default_dynamic_prompts.json"
-llm_chat_url = "https://0xb2962131564bc854ece7b0f7c8c9a8345847abfb.gaia.domains/v1/chat/completions"
+platform = "chat"
+url = "https://0xb2962131564bc854ece7b0f7c8c9a8345847abfb.gaia.domains/v1/chat/completions"
+#prompts_url = "http://localhost:8001/default_dynamic_prompts.json"
 api_key = "gaia-1234"
 history = 5
 

config.toml

@@ -2,12 +2,14 @@ addr = "0.0.0.0:8080"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "Groq"
+platform = "openai"
+url = "https://api.groq.com/openai/v1/audio/speech"
 model = "playai-tts"
 api_key = "gsk_ABCD"
 voice = "Fritz-PlayAI"
 
 [asr]
+platform = "openai"
 url = "https://api.groq.com/openai/v1/audio/transcriptions"
 api_key = "gsk_ABCD"
 model = "whisper-large-v3"
@@ -19,7 +21,8 @@ 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"
+platform = "openai_chat"
+url = "https://api.groq.com/openai/v1/chat/completions"
 api_key = "gsk_ABCD"
 model = "openai/gpt-oss-20b"
 history = 5

docker/server-vad/config.toml

@@ -2,20 +2,23 @@ addr = "0.0.0.0:8080"
 hello_wav = "hello.wav"
 
 [tts]
-platform = "Groq"
+platform = "openai"
+url = "https://api.groq.com/openai/v1/audio/speech"
 model = "playai-tts"
 api_key = "gsk_ABCD"
 voice = "Fritz-PlayAI"
 
 [asr]
+platform = "openai"
 url = "https://api.groq.com/openai/v1/audio/transcriptions"
 api_key = "gsk_ABCD"
 model = "whisper-large-v3"
 lang = "en"
 prompt = "Hello\n你好\n(noise)\n(bgm)\n(silence)\n"
 
 [llm]
-llm_chat_url = "https://api.groq.com/openai/v1/chat/completions"
+platform = "openai_chat"
+url = "https://api.groq.com/openai/v1/chat/completions"
 api_key = "gsk_ABCD"
 model = "openai/gpt-oss-20b"
 history = 5

docker/server/config.toml

@@ -4,18 +4,21 @@ hello_wav = "hello.wav"
 # Get your API key from https://bailian.console.aliyun.com/
 
 [asr]
+platform = "paraformer_v2"
 paraformer_token = "sk-API-KEY"
 
+
 [tts]
-platform = "CosyVoice"
+platform = "cosyvoice"
 token = "sk-API-KEY"
 speaker = "longhua_v2"
 
 # Supported platforms: cosyvoice-v2 (default) and cosyvoice-v1
 # Get speaker list from https://help.aliyun.com/zh/model-studio/cosyvoice-java-sdk#722dd7ca66a6x
 
 [llm]
-llm_chat_url = "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions"
+platform = "openai_chat"
+url = "https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions"
 api_key = "sk-API-KEY"
 model = "qwen-plus"
 history = 5

examples/alibailian/config.toml

@@ -9,6 +9,7 @@ speaker = "cooper"
 
 # Requires a local Whisper API server at port 9092: https://llamaedge.com/docs/ai-models/speech-to-text/quick-start-whisper
 [asr]
+platform = "whisper"
 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
@@ -17,7 +18,8 @@ vad_url = "http://localhost:9093/v1/audio/vad"
 
 # Requires a local LlamaEdge API server at port 9091: https://llamaedge.com/docs/ai-models/llm/quick-start-llm
 [llm]
-llm_chat_url = "http://localhost:9091/v1/chat/completions"
+platform = "chat"
+url = "http://localhost:9091/v1/chat/completions"
 api_key = "Bearer gaia-1234"
 model = "default"
 history = 5

examples/gaia/config.toml

@@ -7,13 +7,15 @@ url = "http://localhost:9094/v1/audio/stream_speech"
 speaker = "cooper"
 
 [asr]
+platform = "whisper"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # vad_url = "http://localhost:9093/v1/audio/vad"
 vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [llm]
-llm_chat_url = "http://localhost:9091/v1/chat/completions"
+platform = "chat"
+url = "http://localhost:9091/v1/chat/completions"
 api_key = "Bearer gaia-1234"
 history = 5
 

examples/gaia/english_teacher/config.toml

@@ -7,13 +7,15 @@ url = "http://localhost:9094/v1/audio/stream_speech"
 speaker = "cooper"
 
 [asr]
+platform = "whisper"
 url = "http://localhost:9092/v1/audio/transcriptions"
 lang = "auto"
 # vad_url = "http://localhost:9093/v1/audio/vad"
 vad_realtime_url = "ws://localhost:9093/v1/audio/realtime_vad"
 
 [llm]
-llm_chat_url = "http://localhost:9091/v1/chat/completions"
+platform = "chat"
+url = "http://localhost:9091/v1/chat/completions"
 api_key = "Bearer gaia-1234"
 history = 5