Merge pull request #400 from TEN-framework/feat_minimax_tts

Feat minimax tts
TEN-framework · Nov 14, 2024 · 9b47b06 · 9b47b06
2 parents df965d2 + 3df22f5
commit 9b47b06
Show file tree

Hide file tree

Showing 16 changed files with 1,269 additions and 1 deletion.
diff --git a/.env.example b/.env.example
@@ -91,6 +91,11 @@ GEMINI_API_KEY=
 #         AWS_REGION_NAME=<aws-region-name>
 LITELLM_MODEL=gpt-4o-mini
 
+# Extension: minimax_tts
+# Minimax TTS key
+MINIMAX_TTS_API_KEY=
+MINIMAX_TTS_GROUP_ID=
+
 # Extension: openai_chatgpt
 # OpenAI API key
 OPENAI_API_BASE=https://api.openai.com/v1

diff --git a/agents/property.json b/agents/property.json
@@ -4575,7 +4575,190 @@
             ]
           }
         ]
+      },
+      {
+        "name": "va_openai_minimax",
+        "auto_start": false,
+        "nodes": [
+          {
+            "type": "extension",
+            "extension_group": "default",
+            "addon": "agora_rtc",
+            "name": "agora_rtc",
+            "property": {
+              "app_id": "${env:AGORA_APP_ID}",
+              "token": "<agora_token>",
+              "channel": "ten_agents_test",
+              "stream_id": 1234,
+              "remote_stream_id": 123,
+              "subscribe_audio": true,
+              "publish_audio": true,
+              "publish_data": true,
+              "enable_agora_asr": true,
+              "agora_asr_vendor_name": "microsoft",
+              "agora_asr_language": "en-US",
+              "agora_asr_vendor_key": "${env:AZURE_STT_KEY}",
+              "agora_asr_vendor_region": "${env:AZURE_STT_REGION}",
+              "agora_asr_session_control_file_path": "session_control.conf"
+            }
+          },
+          {
+            "type": "extension",
+            "extension_group": "default",
+            "addon": "interrupt_detector",
+            "name": "interrupt_detector"
+          },
+          {
+            "type": "extension",
+            "extension_group": "chatgpt",
+            "addon": "openai_chatgpt",
+            "name": "openai_chatgpt",
+            "property": {
+              "base_url": "${env:OPENAI_API_BASE}",
+              "api_key": "${env:OPENAI_API_KEY}",
+              "frequency_penalty": 0.9,
+              "model": "${env:OPENAI_MODEL}",
+              "max_tokens": 512,
+              "prompt": "",
+              "proxy_url": "${env:OPENAI_PROXY_URL}",
+              "greeting": "TEN Agent connected. How can I help you today?",
+              "max_memory_length": 10
+            }
+          },
+          {
+            "type": "extension",
+            "extension_group": "transcriber",
+            "addon": "message_collector",
+            "name": "message_collector"
+          },
+          {
+            "type": "extension",
+            "extension_group": "tts",
+            "addon": "minimax_tts_python",
+            "name": "minimax_tts",
+            "property": {
+              "api_key": "${env:MINIMAX_TTS_API_KEY}",
+              "group_id": "${env:MINIMAX_TTS_GROUP_ID}",
+              "model": "speech-01-turbo",
+              "request_timeout_seconds": 10,
+              "sample_rate": 32000,
+              "url": "https://api.minimax.chat/v1/t2a_v2",
+              "voice_id": "male-qn-qingse"
+            }
+          }
+        ],
+        "connections": [
+          {
+            "extension_group": "default",
+            "extension": "agora_rtc",
+            "data": [
+              {
+                "name": "text_data",
+                "dest": [
+                  {
+                    "extension_group": "default",
+                    "extension": "interrupt_detector"
+                  },
+                  {
+                    "extension_group": "chatgpt",
+                    "extension": "openai_chatgpt"
+                  },
+                  {
+                    "extension_group": "transcriber",
+                    "extension": "message_collector"
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "extension_group": "chatgpt",
+            "extension": "openai_chatgpt",
+            "data": [
+              {
+                "name": "text_data",
+                "dest": [
+                  {
+                    "extension_group": "tts",
+                    "extension": "minimax_tts"
+                  },
+                  {
+                    "extension_group": "transcriber",
+                    "extension": "message_collector"
+                  }
+                ]
+              }
+            ],
+            "cmd": [
+              {
+                "name": "flush",
+                "dest": [
+                  {
+                    "extension_group": "tts",
+                    "extension": "minimax_tts"
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "extension_group": "tts",
+            "extension": "minimax_tts",
+            "audio_frame": [
+              {
+                "name": "pcm_frame",
+                "dest": [
+                  {
+                    "extension_group": "default",
+                    "extension": "agora_rtc"
+                  }
+                ]
+              }
+            ],
+            "cmd": [
+              {
+                "name": "flush",
+                "dest": [
+                  {
+                    "extension_group": "default",
+                    "extension": "agora_rtc"
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "extension_group": "transcriber",
+            "extension": "message_collector",
+            "data": [
+              {
+                "name": "data",
+                "dest": [
+                  {
+                    "extension_group": "default",
+                    "extension": "agora_rtc"
+                  }
+                ]
+              }
+            ]
+          },
+          {
+            "extension_group": "default",
+            "extension": "interrupt_detector",
+            "cmd": [
+              {
+                "name": "flush",
+                "dest": [
+                  {
+                    "extension_group": "chatgpt",
+                    "extension": "openai_chatgpt"
+                  }
+                ]
+              }
+            ]
+          }
+        ]
       }
     ]
   }
-}
+}
diff --git a/agents/ten_packages/extension/minimax_tts/go.mod b/agents/ten_packages/extension/minimax_tts/go.mod
@@ -0,0 +1,12 @@
+module minimax_tts
+
+go 1.20
+
+replace ten_framework => ../../system/ten_runtime_go/interface
+
+require (
+	github.com/go-resty/resty/v2 v2.16.0
+	ten_framework v0.0.0-00010101000000-000000000000
+)
+
+require golang.org/x/net v0.27.0 // indirect
diff --git a/agents/ten_packages/extension/minimax_tts/go.sum b/agents/ten_packages/extension/minimax_tts/go.sum
@@ -0,0 +1,5 @@
+github.com/go-resty/resty/v2 v2.16.0 h1:qpKalHWI2bpp9BIKlyT8TYWEJXOk1NuKbfiT3RRnzWc=
+github.com/go-resty/resty/v2 v2.16.0/go.mod h1:0fHAoK7JoBy/Ch36N8VFeMsK7xQOHhvWaC3iOktwmIU=
+golang.org/x/net v0.27.0 h1:5K3Njcw06/l2y9vpGCSdcxWOYHOUk3dVNGDXN+FvAys=
+golang.org/x/net v0.27.0/go.mod h1:dDi0PyhWNoiUOrAS8uXv/vnScO4wnHQO4mj9fn/RytE=
+golang.org/x/time v0.6.0 h1:eTDhh4ZXt5Qf0augr54TN6suAUudPcawVZeIAPU7D4U=
diff --git a/agents/ten_packages/extension/minimax_tts/manifest.json b/agents/ten_packages/extension/minimax_tts/manifest.json
@@ -0,0 +1,62 @@
+{
+    "type": "extension",
+    "name": "minimax_tts",
+    "version": "0.1.0",
+    "dependencies": [
+        {
+            "type": "system",
+            "name": "ten_runtime_go",
+            "version": "0.3"
+        }
+    ],
+    "api": {
+        "property": {
+            "api_key": {
+                "type": "string"
+            },
+            "group_id": {
+                "type": "string"
+            },
+            "model": {
+                "type": "string"
+            },
+            "request_timeout_seconds": {
+                "type": "int64"
+            },
+            "sample_rate": {
+                "type": "int64"
+            },
+            "url": {
+                "type": "string"
+            },
+            "voice_id": {
+                "type": "string"
+            }
+        },
+        "data_in": [
+            {
+                "name": "text_data",
+                "property": {
+                    "text": {
+                        "type": "string"
+                    }
+                }
+            }
+        ],
+        "cmd_in": [
+            {
+                "name": "flush"
+            }
+        ],
+        "cmd_out": [
+            {
+                "name": "flush"
+            }
+        ],
+        "audio_frame_out": [
+            {
+                "name": "pcm_frame"
+            }
+        ]
+    }
+}