Add alltalk TTS

agixt/extensions/alltalk_tts.py

@@ -0,0 +1,35 @@
+import requests
+import base64
+import uuid
+from Extensions import Extensions
+
+
+class alltalk_tts(Extensions):
+    def __init__(
+        self,
+        voice: str = "default",
+        **kwargs,
+    ):
+        self.voice = voice
+        self.commands = {
+            "Speak with TTS with Alltalk Text to Speech": self.speak_with_alltalk_tts
+        }
+
+    async def speak_with_alltalk_tts(
+        self,
+        text: str,
+    ):
+        data = {
+            "text": text,
+            "voice": self.voice,
+            "language": "en",
+            "temperature": 0.7,
+            "repetition_penalty": 10.0,
+            "output_file": f"{uuid.uuid4()}.wav",
+            "streaming": False,
+        }
+        response = requests.post(
+            "http://alltalk-tts:7851/api/generate",
+            json=data,
+        )
+        return f"{text}\n#GENERATED_AUDIO:{base64.b64encode(response.content).decode('utf-8')}"

alltalk.json

@@ -0,0 +1,25 @@
+{
+    "activate": true,
+    "autoplay": true,
+    "branding": "AllTalk ",
+    "narrator_enabled": false,
+    "deepspeed_activate": true,
+    "delete_output_wavs": "Disabled",
+    "ip_address": "127.0.0.1",
+    "language": "English",
+    "low_vram": false,
+    "local_temperature": "0.7",
+    "local_repetition_penalty": "10.0",
+    "tts_model_loaded": true,
+    "tts_model_name": "tts_models/multilingual/multi-dataset/xtts_v2",
+    "narrator_voice": "female_01.wav",
+    "output_folder_wav": "extensions/alltalk_tts/outputs/",
+    "output_folder_wav_standalone": "outputs/",
+    "port_number": "7851",
+    "remove_trailing_dots": false,
+    "show_text": true,
+    "tts_method_api_local": false,
+    "tts_method_api_tts": false,
+    "tts_method_xtts_local": true,
+    "voice": "female_01.wav"
+}

docker-compose-dev-cuda.yml

@@ -58,4 +58,29 @@ services:
     ports:
       - "8091:8091"
     volumes:
-      - ./models:/app/models
+      - ./models:/app/models
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]
+  alltalk-tts:
+    image: joshxt/alltalk_tts:cuda
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./WORKSPACE/outputs:/app/outputs/
+      - ./models:/app/models/
+      - ./voices:/app/voices/
+      - ./finetune/put-voice-samples-in-here:/app/finetune/put-voice-samples-in-here
+      - ./alltalk.json:/app/confignew.json
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: all
+              capabilities: [ gpu ]

docker-compose-dev.yml

@@ -56,4 +56,15 @@ services:
     ports:
       - "8091:8091"
     volumes:
-      - ./models:/app/models
+      - ./models:/app/models
+  alltalk-tts:
+    image: joshxt/alltalk_tts:cpu
+    restart: unless-stopped
+    ports:
+      - "7851:7851"
+    volumes:
+      - ./WORKSPACE/outputs:/app/outputs/
+      - ./WORKSPACE/audio-samples:/app/finetune/put-voice-samples-in-here/
+      - ./models:/app/models/
+      - ./voices:/app/voices/
+      - ./alltalk.json:/app/confignew.json