Merge branch 'vocodedev-main'

.github/workflows/stale.yml

@@ -0,0 +1,28 @@
+name: "Close stale issues"
+
+on:
+  schedule:
+    - cron: "30 1 * * *"
+
+permissions:
+  contents: write
+  issues: write
+  pull-requests: write
+
+jobs:
+  stale:
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/stale@v9
+      with:
+        repo-token: ${{ secrets.GITHUB_TOKEN }}
+        days-before-stale: 60
+        days-before-close: 7
+        stale-issue-label: 'stale'
+        stale-issue-message: 'This issue has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.'
+        close-issue-message: 'This issue has been automatically closed due to inactivity. Thank you for your contributions.'
+        stale-pr-label: 'stale'
+        stale-pr-message: 'This PR has been automatically marked as stale because it has not had recent activity. It will be closed if no further activity occurs. Thank you for your contributions.'
+        close-pr-message: 'This PR has been automatically closed due to inactivity. Thank you for your contributions.'
+        exempt-all-pr-milestones: true
+        enable-statistics: true

.github/workflows/test.yml

@@ -20,7 +20,7 @@ jobs:
           - "3.10"
           - "3.11"
         poetry-version:
-          - "1.4.2"
+          - "1.7.1"
 
     runs-on: ubuntu-latest
 

.pre-commit-config.yaml

@@ -4,7 +4,7 @@ repos:
     hooks:
     -   id: black
 -   repo: https://github.com/pre-commit/mirrors-mypy
-    rev: v1.3.0
+    rev: v1.8.0
     hooks:
     -   id: mypy
         args: [--ignore-missing-imports, ./]

apps/client_backend/pyproject.toml

@@ -8,7 +8,7 @@ readme = "README.md"
 [tool.poetry.dependencies]
 python = ">=3.9,<3.12"
 python-dotenv = "^1.0.0"
-vocode = "0.1.111a3"
+vocode = "0.1.111"
 elevenlabs = "^0.2.23"
 
 

apps/langchain_agent/README.md

@@ -1,3 +1,3 @@
 # langchain_agent
 
-See https://docs.vocode.dev/langchain-agent for setup steps!
+See https://docs.vocode.dev/open-source/langchain-agent for setup steps!

apps/langchain_agent/pyproject.toml

@@ -11,7 +11,7 @@ redis = "^4.5.4"
 twilio = "^8.1.0"
 vonage = "^3.5.1"
 python-dotenv = "^1.0.0"
-vocode = "0.1.111a3"
+vocode = "0.1.111"
 google-cloud-texttospeech = "^2.14.1"
 
 

apps/telegram_bot/Dockerfile

@@ -1,4 +1,4 @@
-FROM python:3.11
+FROM python:3.9-bullseye
 
 # get portaudio and ffmpeg
 RUN apt-get update \

apps/telegram_bot/main.py

@@ -4,7 +4,7 @@
 import logging
 import inspect
 from collections import defaultdict
-from pydantic import BaseModel
+from pydantic.v1 import BaseModel
 from typing import Tuple, Union, Optional, Dict, Type, List
 from pydub import AudioSegment
 from telegram import Update
@@ -28,6 +28,10 @@
     BaseSynthesizer,
 )
 
+from dotenv import load_dotenv
+
+load_dotenv()
+
 logging.basicConfig(
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s", level=logging.INFO
 )
@@ -46,7 +50,7 @@
 # Required environment variables containing API key: OPENAI_API_KEY, TELEGRAM_BOT_KEY, and your Vocode synthesizers classes corresponding API key variable
 
 # Your chosen synthesizer provider's corresponding Vocode turn_based class instance
-SYNTH = CoquiSynthesizer(use_xtts=True)
+SYNTH = AzureSynthesizer(voice_name="en-US-SteffanNeural")
 
 # Instructions to the language model responsible for generating response transcript.
 SYSTEM_PROMPT = "You are having a voice-to-voice conversation with a user. Always pretend you are a real human. Do not avoid or decline to answer questions because you are not human."
@@ -76,33 +80,36 @@
 
 # Define a Voice model with id, name and description fields
 class Voice(BaseModel):
-  id: Optional[str] = None # Optional id for the voice
-  name: Optional[str] = None # Optional name for the voice
-  description: Optional[str] = None # Optional description for the voice
+    id: Optional[str] = None  # Optional id for the voice
+    name: Optional[str] = None  # Optional name for the voice
+    description: Optional[str] = None  # Optional description for the voice
+
 
 # Array of tuples (synthesizer's voice id, nickname, description if text to voice)
 DEFAULT_VOICES: List[Voice] = [Voice(id=None, name="Coqui Default", description=None)]
 
+
 # Define a Chat model with voices, current_voice and current_conversation fields
 class Chat(BaseModel):
-    voices: List[Voice] = DEFAULT_VOICES # List of available voices for the chat
-    current_voice: Voice = DEFAULT_VOICES[0] # Current voice for the chat
-    current_conversation: Optional[bytes] = None # Current conversation as a pickled object
+    voices: List[Voice] = DEFAULT_VOICES  # List of available voices for the chat
+    current_voice: Voice = DEFAULT_VOICES[0]  # Current voice for the chat
+    current_conversation: Optional[
+        bytes
+    ] = None  # Current conversation as a pickled object
 
 
 class VocodeBotResponder:
     def __init__(
         self,
         transcriber: BaseTranscriber,
         system_prompt: str,
-        synthesizer: BaseSynthesizer
+        synthesizer: BaseSynthesizer,
     ) -> None:
         self.transcriber = transcriber
         self.system_prompt = system_prompt
         self.synthesizer = synthesizer
         self.db: Dict[int, Chat] = defaultdict(Chat)
 
-
     def get_agent(self, chat_id: int) -> ChatGPTAgent:
         # Get current voice name and description from DB
         user = self.db[chat_id]
@@ -142,13 +149,16 @@ async def get_response(
         voice_description = user.current_voice.description
 
         # If we have a Coqui voice prompt, use that. Otherwise, set ID as synthesizer expects.
-        if voice_description is not None and isinstance(self.synthesizer, CoquiSynthesizer):
+        if voice_description is not None and isinstance(
+            self.synthesizer, CoquiSynthesizer
+        ):
             self.synthesizer.voice_prompt = voice_description
         elif voice_id is not None:
             setattr(self.synthesizer, voice_attr_of[type(self.synthesizer)], voice_id)
 
         # Synthesize response
-        synth_response = await self.synthesizer.async_synthesize(agent_response)
+        # TODO make async
+        synth_response = self.synthesizer.synthesize(agent_response)
 
         # Save conversation to DB
         self.db[chat_id].current_conversation = pickle.dumps(agent.memory)
@@ -162,7 +172,9 @@ async def handle_telegram_start(
         start_text = """
 I'm a voice chatbot, send a voice message to me and I'll send one back!" Use /help to see available commands.
 """
-        await context.bot.send_message(chat_id=update.effective_chat.id, text=start_text)
+        await context.bot.send_message(
+            chat_id=update.effective_chat.id, text=start_text
+        )
 
     async def handle_telegram_message(
         self, update: Update, context: ContextTypes.DEFAULT_TYPE
@@ -302,7 +314,7 @@ async def handle_telegram_help(
 - Use /help to see this help message again.
 """
         assert update.effective_chat, "Chat must be defined!"
-        if isinstance(self.synthesizer, CoquiSynthesizer): 
+        if isinstance(self.synthesizer, CoquiSynthesizer):
             help_text += "\n- Use /create <voice_description> to create a new Coqui voice from a text prompt and switch to it."
         await context.bot.send_message(chat_id=update.effective_chat.id, text=help_text)