feat: nova-3 example

2025-02-18 11:24:02 +08:00
30 changed files with 61 additions and 11532 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -32,21 +32,6 @@ fly.toml

 # Example files
 pipecat/examples/twilio-chatbot/templates/streams.xml
-pipecat/examples/bot-ready-signalling/client/react-native/node_modules/
-pipecat/examples/bot-ready-signalling/client/react-native/.expo/
-pipecat/examples/bot-ready-signalling/client/react-native/dist/
-pipecat/examples/bot-ready-signalling/client/react-native/npm-debug.*
-pipecat/examples/bot-ready-signalling/client/react-native/*.jks
-pipecat/examples/bot-ready-signalling/client/react-native/*.p8
-pipecat/examples/bot-ready-signalling/client/react-native/*.p12
-pipecat/examples/bot-ready-signalling/client/react-native/*.key
-pipecat/examples/bot-ready-signalling/client/react-native/*.mobileprovision
-pipecat/examples/bot-ready-signalling/client/react-native/*.orig.*
-pipecat/examples/bot-ready-signalling/client/react-native/web-build/
-
-# macOS
-.DS_Store
-

 # Documentation
 docs/api/_build/
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -5,37 +5,6 @@ All notable changes to **Pipecat** will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

-## Unreleased
-
-### Added
-
- Added `room_url` property to `DailyTransport`.
-
- Added `addons` argument to `DeepgramSTTService`.
-
- Added `exponential_backoff_time()` to `utils.network` module.
-
-### Changed
-
- `DeepgramSTTService` now uses the new `nova-3` model by default. If you want
-  to use the previous model you can pass `LiveOptions(model="nova-2-general")`.
-  (see https://deepgram.com/learn/introducing-nova-3-speech-to-text-api)
-
-```python
-stt = DeepgramSTTService(..., live_options=LiveOptions(model="nova-2-general"))
-```
-
-### Fixed
-
- Fixed an issue that `start_callback` was not invoked for some LLM services.
-
- Fixed an issue that would cause `DeepgramSTTService` to stop working after an
-  error occurred (e.g. sudden network loss). If the network recovered we would
-  not reconnect.
-
- Fixed a `STTMuteFilter` issue that would not mute user audio frames causing
-  transcriptions to be generated by the STT service.
-
 ## [0.0.57] - 2025-02-14

 ### Added
--- a/examples/bot-ready-signalling/client/react-native/.nvmrc
+++ b/examples/bot-ready-signalling/client/react-native/.nvmrc
@@ -1 +0,0 @@
-22.14
--- a/examples/bot-ready-signalling/client/react-native/README.md
+++ b/examples/bot-ready-signalling/client/react-native/README.md
@@ -1,60 +0,0 @@
-# React Native Implementation
-
-Basic implementation using the [Pipecat React Native SDK](https://docs.pipecat.ai/client/react-native/introduction).
-
-## Usage
-
-### Expo requirements
-
-This project cannot be used with an [Expo Go](https://docs.expo.dev/workflow/expo-go/) app because [it requires custom native code](https://docs.expo.io/workflow/customizing/).
-
-When a project requires custom native code or a config plugin, we need to transition from using [Expo Go](https://docs.expo.dev/workflow/expo-go/) 
-to a [development build](https://docs.expo.dev/development/introduction/).
-
-More details about the custom native code used by this demo can be found in [rn-daily-js-expo-config-plugin](https://github.com/daily-co/rn-daily-js-expo-config-plugin).
-
-### Building remotely
-
-If you do not have experience with Xcode and Android Studio builds or do not have them installed locally on your computer, you will need to follow [this guide from Expo to use EAS Build](https://docs.expo.dev/development/create-development-builds/#create-and-install-eas-build).
-
-### Building locally
-
-You will need to have installed locally on your computer:
- [Xcode](https://developer.apple.com/xcode/) to build for iOS;
- [Android Studio](https://developer.android.com/studio) to build for Android;
-
-#### Install the demo dependencies
-
-```bash
-# Use the version of node specified in .nvmrc
-nvm i
-
-# Install dependencies
-npm i
-
-# Before a native app can be compiled, the native source code must be generated.
-npx expo prebuild
-
-# Configure the environment variable to connect to the local server
-cp env.example .env
-# edit .env and add your local ip address, for example: http://192.168.1.16:7860
-```
-
-#### Running on Android
-
-After plugging in an Android device [configured for debugging](https://developer.android.com/studio/debug/dev-options), run the following command:
-
-```
-npm run android
-```
-
-#### Running on iOS
-
-Run the following command:
-
-```
-npm run ios
-```
-
-#### Connect to the server
-Use the http://localhost:5173 in your app.
--- a/examples/bot-ready-signalling/client/react-native/app.json
+++ b/examples/bot-ready-signalling/client/react-native/app.json
@@ -1,75 +0,0 @@
-{
-  "expo": {
-    "name": "bot-ready-rn",
-    "slug": "bot-ready-rn",
-    "version": "1.0.0",
-    "orientation": "portrait",
-    "icon": "./assets/icon.png",
-    "userInterfaceStyle": "light",
-    "splash": {
-      "image": "./assets/splash.png",
-      "resizeMode": "contain",
-      "backgroundColor": "#ffffff"
-    },
-    "updates": {
-      "fallbackToCacheTimeout": 0
-    },
-    "assetBundlePatterns": [
-      "**/*"
-    ],
-    "ios": {
-      "supportsTablet": true,
-      "bitcode": false,
-      "bundleIdentifier": "co.daily.expo.BotReady",
-      "infoPlist": {
-        "UIBackgroundModes": [
-          "voip"
-        ]
-      },
-      "appleTeamId": "EEBGKV9N3N"
-    },
-    "android": {
-      "adaptiveIcon": {
-        "foregroundImage": "./assets/adaptive-icon.png",
-        "backgroundColor": "#FFFFFF"
-      },
-      "package": "co.daily.expo.BotReady",
-      "permissions": [
-        "android.permission.ACCESS_NETWORK_STATE",
-        "android.permission.BLUETOOTH",
-        "android.permission.CAMERA",
-        "android.permission.INTERNET",
-        "android.permission.MODIFY_AUDIO_SETTINGS",
-        "android.permission.RECORD_AUDIO",
-        "android.permission.SYSTEM_ALERT_WINDOW",
-        "android.permission.WAKE_LOCK",
-        "android.permission.FOREGROUND_SERVICE",
-        "android.permission.FOREGROUND_SERVICE_CAMERA",
-        "android.permission.FOREGROUND_SERVICE_MICROPHONE",
-        "android.permission.FOREGROUND_SERVICE_MEDIA_PROJECTION",
-        "android.permission.POST_NOTIFICATIONS"
-      ]
-    },
-    "web": {
-      "favicon": "./assets/favicon.png"
-    },
-    "plugins": [
-      "@config-plugins/react-native-webrtc",
-      "@daily-co/config-plugin-rn-daily-js",
-      [
-        "expo-build-properties",
-        {
-          "android": {
-            "minSdkVersion": 24,
-            "compileSdkVersion": 35,
-            "targetSdkVersion": 34,
-            "buildToolsVersion": "35.0.0"
-          },
-          "ios": {
-            "deploymentTarget": "15.1"
-          }
-        }
-      ]
-    ]
-  }
-}
--- a/examples/bot-ready-signalling/client/react-native/assets/adaptive-icon.png
+++ b/examples/bot-ready-signalling/client/react-native/assets/adaptive-icon.png
--- a/examples/bot-ready-signalling/client/react-native/assets/favicon.png
+++ b/examples/bot-ready-signalling/client/react-native/assets/favicon.png
--- a/examples/bot-ready-signalling/client/react-native/assets/icon.png
+++ b/examples/bot-ready-signalling/client/react-native/assets/icon.png
--- a/examples/bot-ready-signalling/client/react-native/assets/splash.png
+++ b/examples/bot-ready-signalling/client/react-native/assets/splash.png
--- a/examples/bot-ready-signalling/client/react-native/babel.config.js
+++ b/examples/bot-ready-signalling/client/react-native/babel.config.js
@@ -1,7 +0,0 @@
-module.exports = function(api) {
-  api.cache(true);
-  return {
-    presets: ['babel-preset-expo'],
-    plugins: [["module:react-native-dotenv"]],
-  };
-};
--- a/examples/bot-ready-signalling/client/react-native/env.example
+++ b/examples/bot-ready-signalling/client/react-native/env.example
@@ -1 +0,0 @@
-API_BASE_URL=http://YOUR_LOCAL_IP:7860
--- a/examples/bot-ready-signalling/client/react-native/index.js
+++ b/examples/bot-ready-signalling/client/react-native/index.js
@@ -1,7 +0,0 @@
-import { registerRootComponent } from "expo";
-
-import App from "./src/App";
-
-// registerRootComponent calls AppRegistry.registerComponent('main', () => App);
-// It also ensures that the environment is set up appropriately
-registerRootComponent(App);
--- a/examples/bot-ready-signalling/client/react-native/metro.config.js
+++ b/examples/bot-ready-signalling/client/react-native/metro.config.js
@@ -1,4 +0,0 @@
-// Learn more https://docs.expo.io/guides/customizing-metro
-const { getDefaultConfig } = require('expo/metro-config');
-
-module.exports = getDefaultConfig(__dirname);
--- a/examples/bot-ready-signalling/client/react-native/package-lock.json
+++ b/examples/bot-ready-signalling/client/react-native/package-lock.json
--- a/examples/bot-ready-signalling/client/react-native/package.json
+++ b/examples/bot-ready-signalling/client/react-native/package.json
@@ -1,31 +0,0 @@
-{
-  "name": "bot-ready-rn",
-  "version": "1.0.0",
-  "scripts": {
-    "start": "expo start --dev-client",
-    "android": "expo run:android --device",
-    "ios": "expo run:ios --device",
-    "web": "expo start --web"
-  },
-  "dependencies": {
-    "@config-plugins/react-native-webrtc": "^10.0.0",
-    "@daily-co/config-plugin-rn-daily-js": "0.0.7",
-    "@daily-co/react-native-daily-js": "^0.70.0",
-    "@daily-co/react-native-webrtc": "^118.0.3-daily.2",
-    "@react-native-async-storage/async-storage": "1.23.1",
-    "expo": "^52.0.0",
-    "expo-build-properties": "~0.13.1",
-    "expo-dev-client": "~5.0.5",
-    "expo-splash-screen": "~0.29.16",
-    "expo-status-bar": "~2.0.0",
-    "react": "18.3.1",
-    "react-native": "0.76.3",
-    "react-native-background-timer": "^2.4.1",
-    "react-native-dotenv": "^3.4.11",
-    "react-native-get-random-values": "^1.11.0"
-  },
-  "devDependencies": {
-    "@babel/core": "^7.12.9"
-  },
-  "private": true
-}
--- a/examples/bot-ready-signalling/client/react-native/src/App.js
+++ b/examples/bot-ready-signalling/client/react-native/src/App.js
@@ -1,121 +0,0 @@
-import React, { useState, useEffect } from 'react';
-import {SafeAreaView, View, Text, Button, StyleSheet, ScrollView} from 'react-native';
-import Daily from "@daily-co/react-native-daily-js";
-import { API_BASE_URL } from "@env";
-
-const CallScreen = () => {
-  const [connectionStatus, setConnectionStatus] = useState('Disconnected');
-  const [isConnected, setIsConnected] = useState(false);
-  const [callObject, setCallObject] = useState(null);
-  const [logs, setLogs] = useState([]);
-
-  useEffect(() => {
-    if (callObject) {
-      setupTrackListeners(callObject);
-    }
-  }, [callObject]);
-
-  const log = (message) => {
-    setLogs((prevLogs) => [...prevLogs, `${new Date().toISOString()} - ${message}`]);
-    console.log(message);
-  };
-
-  const setupTrackListeners = (callObject) => {
-    callObject.on("joined-meeting", () => {
-      setConnectionStatus('Connected');
-      setIsConnected(true);
-      log('Client connected');
-    });
-    callObject.on("left-meeting", () => {
-      setConnectionStatus('Disconnected');
-      setIsConnected(false);
-      log('Client disconnected');
-    });
-    callObject.on("participant-left", () => {
-      // When the bot leaves, we are also disconnecting from the call
-      disconnect().catch((err) => {
-        log(`Failed to disconnect ${err}`);
-      })
-    });
-    // Trigger so the bot can start sending audio
-    callObject.on("track-started", (evt) => {
-      if (evt.track.kind === "audio" && evt.participant.local === false) {
-        handleEventToConsole(evt)
-        log("Sending the message that will trigger the bot to play the audio.")
-        callObject.sendAppMessage("playable")
-      }
-    });
-    callObject.on("error", (evt) => log(`Error: ${evt.error}`));
-    // Other events just for awareness
-    callObject.on("track-stopped", handleEventToConsole);
-    callObject.on("participant-joined", handleEventToConsole);
-    callObject.on("participant-updated", handleEventToConsole);
-  };
-
-  const handleEventToConsole = (evt) => {
-    log(`Received event: ${evt.action}`);
-  };
-
-  const connect = async () => {
-    try {
-      const callObject = Daily.createCallObject({ subscribeToTracksAutomatically: true });
-      setCallObject(callObject);
-      const connectionUrl = `${API_BASE_URL}/connect`
-      const res = await fetch(connectionUrl, { method: "POST", headers: { "Content-Type": "application/json" } });
-      const roomInfo = await res.json();
-      await callObject.join({ url: roomInfo.room_url });
-    } catch (error) {
-      log(`Error connecting: ${error.message}`);
-    }
-  };
-
-  const disconnect = async () => {
-    if (callObject) {
-      try {
-        await callObject.leave();
-        await callObject.destroy();
-        setCallObject(null);
-      } catch (error) {
-        log(`Error disconnecting: ${error.message}`);
-      }
-    }
-  };
-
-  return (
-      <SafeAreaView style={styles.safeArea}>
-        <View style={styles.container}>
-          <View style={styles.statusBar}>
-            <Text>Status: <Text style={styles.status}>{connectionStatus}</Text></Text>
-            <View style={styles.controls}>
-              <Button
-                title={isConnected ? "Disconnect" : "Connect"}
-                onPress={isConnected ? disconnect : connect}
-              />
-            </View>
-          </View>
-
-          <View style={styles.debugPanel}>
-            <Text style={styles.debugTitle}>Debug Info</Text>
-            <ScrollView style={styles.debugLog}>
-              {logs.map((logEntry, index) => (
-                  <Text key={index} style={styles.logText}>{logEntry}</Text>
-              ))}
-            </ScrollView>
-          </View>
-        </View>
-      </SafeAreaView>
-  );
-};
-
-const styles = StyleSheet.create({
-  safeArea: { flex: 1, backgroundColor: '#f0f0f0', padding: 20 },
-  container: { flex: 1, margin: 20 },
-  statusBar: { flexDirection: 'row', justifyContent: 'space-between', alignItems: 'center', padding: 10, backgroundColor: '#fff', borderRadius: 8, marginBottom: 20 },
-  status: { fontWeight: 'bold' },
-  controls: { flexDirection: 'row', gap: 10 },
-  debugPanel: { height: '80%', backgroundColor: '#fff', borderRadius: 8, padding: 20},
-  debugTitle: { fontSize: 16, fontWeight: 'bold' },
-  debugLog: { height: '100%', overflow: 'scroll', backgroundColor: '#f8f8f8', padding: 10, borderRadius: 4, fontFamily: 'monospace', fontSize: 12, lineHeight: 1.4 },
-});
-
-export default CallScreen;
--- a/examples/foundational/07-interruptible.py
+++ b/examples/foundational/07-interruptible.py
@@ -21,11 +21,6 @@ from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.openai import OpenAILLMService
 from pipecat.transports.services.daily import DailyParams, DailyTransport
-from pipecat.transports.services.helpers.daily_rest import (
-    DailyMeetingTokenParams,
-    DailyRESTHelper,
-    DailyRoomParams,
-)

 load_dotenv(override=True)

@@ -35,31 +30,10 @@ logger.add(sys.stderr, level="DEBUG")

 async def main():
    async with aiohttp.ClientSession() as session:
-        daily_rest_helper = DailyRESTHelper(
-            daily_api_key=os.getenv("DAILY_API_KEY"),
-            daily_api_url=os.getenv("DAILY_API_URL", "https://api.daily.co/v1"),
-            aiohttp_session=session,
-        )
-
-        room = await daily_rest_helper.create_room(
-            params=DailyRoomParams(properties={"enable_recording": "cloud"})
-        )
-
-        params = DailyMeetingTokenParams(
-            properties={
-                "enable_recording": "cloud",
-                "start_cloud_recording": True,
-            }
-        )
-
-        token = await daily_rest_helper.get_token(
-            room_url=room.url, expiry_time=60 * 60, params=params
-        )
-
-        logger.debug(f"Room URL: {room.url} Room token: {token}")
+        (room_url, token) = await configure(session)

        transport = DailyTransport(
-            room.url,
+            room_url,
            token,
            "Respond bot",
            DailyParams(
@@ -111,7 +85,6 @@ async def main():
        @transport.event_handler("on_first_participant_joined")
        async def on_first_participant_joined(transport, participant):
            await transport.capture_participant_transcription(participant["id"])
-            # await transport.start_recording()
            # Kick off the conversation.
            messages.append({"role": "system", "content": "Please introduce yourself to the user."})
            await task.queue_frames([context_aggregator.user().get_context_frame()])
--- a/examples/foundational/07c-interruptible-deepgram.py
+++ b/examples/foundational/07c-interruptible-deepgram.py
@@ -9,6 +9,7 @@ import os
 import sys

 import aiohttp
+from deepgram import LiveOptions
 from dotenv import load_dotenv
 from loguru import logger
 from runner import configure
@@ -44,7 +45,23 @@ async def main():
            ),
        )

-        stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        # stt = DeepgramSTTService(api_key=os.getenv("DEEPGRAM_API_KEY"))
+        stt = DeepgramSTTService(
+            api_key=os.getenv("DEEPGRAM_API_KEY"),
+            # url=deepgram_url,
+            live_options=LiveOptions(
+                encoding="linear16",
+                language="en-US",
+                model="nova-3",
+                channels=1,
+                interim_results=True,
+                # smart_format=smart_format,
+                # endpointing=endpointing,
+                vad_events=True,
+                diarize=True,
+                filler_words=True,
+            ),
+        )

        tts = DeepgramTTSService(api_key=os.getenv("DEEPGRAM_API_KEY"), voice="aura-helios-en")

--- a/examples/foundational/14e-function-calling-gemini.py
+++ b/examples/foundational/14e-function-calling-gemini.py
@@ -14,7 +14,6 @@ from loguru import logger
 from runner import configure

 from pipecat.audio.vad.silero import SileroVADAnalyzer
-from pipecat.frames.frames import TTSSpeakFrame
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
 from pipecat.pipeline.task import PipelineParams, PipelineTask
@@ -31,12 +30,6 @@ logger.add(sys.stderr, level="DEBUG")
 video_participant_id = None


-async def start_fetch_weather(function_name, llm, context):
-    """Push a frame to the LLM; this is handy when the LLM response might take a while."""
-    await llm.push_frame(TTSSpeakFrame("Let me check on that."))
-    logger.debug(f"Starting fetch_weather_from_api with function_name: {function_name}")
-
-
 async def get_weather(function_name, tool_call_id, arguments, llm, context, result_callback):
    location = arguments["location"]
    await result_callback(f"The weather in {location} is currently 72 degrees and sunny.")
@@ -70,7 +63,7 @@ async def main():
        )

        llm = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"), model="gemini-2.0-flash-001")
-        llm.register_function("get_weather", get_weather, start_fetch_weather)
+        llm.register_function("get_weather", get_weather)
        llm.register_function("get_image", get_image)

        tools = [
--- a/examples/translation-chatbot/bot.py
+++ b/examples/translation-chatbot/bot.py
@@ -24,15 +24,17 @@ from pipecat.frames.frames import (
 )
 from pipecat.pipeline.pipeline import Pipeline
 from pipecat.pipeline.runner import PipelineRunner
-from pipecat.pipeline.task import PipelineParams, PipelineTask
+from pipecat.pipeline.task import PipelineTask
 from pipecat.processors.aggregators.openai_llm_context import OpenAILLMContext
 from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
-from pipecat.processors.frameworks.rtvi import RTVIObserver, RTVIProcessor
 from pipecat.processors.transcript_processor import TranscriptProcessor
 from pipecat.services.cartesia import CartesiaTTSService
 from pipecat.services.deepgram import DeepgramSTTService
 from pipecat.services.openai import OpenAILLMService
-from pipecat.transports.services.daily import DailyParams, DailyTransport
+from pipecat.transports.services.daily import (
+    DailyParams,
+    DailyTransport,
+)

 load_dotenv(override=True)

@@ -164,32 +166,21 @@ async def main():
        async def on_transcript_update(processor, frame):
            await transcript_handler.on_transcript_update(processor, frame)

-        rtvi = RTVIProcessor()
-
        pipeline = Pipeline(
            [
                transport.input(),
-                rtvi,
                stt,
                transcript.user(),  # User transcripts
                tp,
                llm,
                tts,
                transport.output(),
-                transcript.assistant(),
                context_aggregator.assistant(),
+                transcript.assistant(),  # Assistant transcripts
            ]
        )

-        task = PipelineTask(
-            pipeline,
-            PipelineParams(
-                allow_interruptions=False,  # We don't want to interrupt the translator bot
-                enable_metrics=True,
-                enable_usage_metrics=True,
-                observers=[RTVIObserver(rtvi)],
-            ),
-        )
+        task = PipelineTask(pipeline)

        @transport.event_handler("on_first_participant_joined")
        async def on_first_participant_joined(transport, participant):
--- a/examples/translation-chatbot/requirements.txt
+++ b/examples/translation-chatbot/requirements.txt
@@ -1,4 +1,4 @@
 python-dotenv
 fastapi[all]
-pipecat-ai[cartesia,daily,deepgram,openai,silero]
+pipecat-ai[daily,openai,azure]
 aiohttp
--- a/src/pipecat/processors/filters/stt_mute_filter.py
+++ b/src/pipecat/processors/filters/stt_mute_filter.py
@@ -23,7 +23,6 @@ from pipecat.frames.frames import (
    Frame,
    FunctionCallInProgressFrame,
    FunctionCallResultFrame,
-    InputAudioRawFrame,
    StartFrame,
    StartInterruptionFrame,
    StopInterruptionFrame,
@@ -186,14 +185,13 @@ class STTMuteFilter(FrameProcessor):
                StopInterruptionFrame,
                UserStartedSpeakingFrame,
                UserStoppedSpeakingFrame,
-                InputAudioRawFrame,
            ),
        ):
            # Only pass VAD-related frames when not muted
            if not self.is_muted:
                await self.push_frame(frame, direction)
            else:
-                logger.trace(f"{frame.__class__.__name__} suppressed - STT currently muted")
+                logger.debug(f"{frame.__class__.__name__} suppressed - STT currently muted")
        else:
            # Pass all other frames through
            await self.push_frame(frame, direction)
--- a/src/pipecat/services/ai_services.py
+++ b/src/pipecat/services/ai_services.py
@@ -175,7 +175,6 @@ class LLMService(AIService):
            f = self._callbacks[None]
        else:
            return None
-        await self.call_start_function(context, function_name)
        await context.call_function(
            f,
            function_name=function_name,
--- a/src/pipecat/services/deepgram.py
+++ b/src/pipecat/services/deepgram.py
@@ -5,7 +5,7 @@
 #

 import asyncio
-from typing import AsyncGenerator, Dict, Optional
+from typing import AsyncGenerator, Optional

 from loguru import logger

@@ -34,7 +34,6 @@ try:
        AsyncListenWebSocketClient,
        DeepgramClient,
        DeepgramClientOptions,
-        ErrorResponse,
        LiveOptions,
        LiveResultResponse,
        LiveTranscriptionEvents,
@@ -121,7 +120,6 @@ class DeepgramSTTService(STTService):
        url: str = "",
        sample_rate: Optional[int] = None,
        live_options: Optional[LiveOptions] = None,
-        addons: Optional[Dict] = None,
        **kwargs,
    ):
        super().__init__(sample_rate=sample_rate, **kwargs)
@@ -129,7 +127,7 @@ class DeepgramSTTService(STTService):
        default_options = LiveOptions(
            encoding="linear16",
            language=Language.EN,
-            model="nova-3-general",
+            model="nova-2-general",
            channels=1,
            interim_results=True,
            smart_format=True,
@@ -149,7 +147,6 @@ class DeepgramSTTService(STTService):
            merged_options.language = merged_options.language.value

        self._settings = merged_options.to_dict()
-        self._addons = addons

        self._client = DeepgramClient(
            api_key,
@@ -158,10 +155,13 @@ class DeepgramSTTService(STTService):
                options={"keepalive": "true"},  # verbose=logging.DEBUG
            ),
        )
-
+        self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1")
+        self._connection.on(LiveTranscriptionEvents.Transcript, self._on_message)
        if self.vad_enabled:
            self._register_event_handler("on_speech_started")
            self._register_event_handler("on_utterance_end")
+            self._connection.on(LiveTranscriptionEvents.SpeechStarted, self._on_speech_started)
+            self._connection.on(LiveTranscriptionEvents.UtteranceEnd, self._on_utterance_end)

    @property
    def vad_enabled(self):
@@ -202,25 +202,7 @@ class DeepgramSTTService(STTService):

    async def _connect(self):
        logger.debug("Connecting to Deepgram")
-
-        self._connection: AsyncListenWebSocketClient = self._client.listen.asyncwebsocket.v("1")
-
-        self._connection.on(
-            LiveTranscriptionEvents(LiveTranscriptionEvents.Transcript), self._on_message
-        )
-        self._connection.on(LiveTranscriptionEvents(LiveTranscriptionEvents.Error), self._on_error)
-
-        if self.vad_enabled:
-            self._connection.on(
-                LiveTranscriptionEvents(LiveTranscriptionEvents.SpeechStarted),
-                self._on_speech_started,
-            )
-            self._connection.on(
-                LiveTranscriptionEvents(LiveTranscriptionEvents.UtteranceEnd),
-                self._on_utterance_end,
-            )
-
-        if not await self._connection.start(options=self._settings, addons=self._addons):
+        if not await self._connection.start(self._settings):
            logger.error(f"{self}: unable to connect to Deepgram")

    async def _disconnect(self):
@@ -232,15 +214,6 @@ class DeepgramSTTService(STTService):
        await self.start_ttfb_metrics()
        await self.start_processing_metrics()

-    async def _on_error(self, *args, **kwargs):
-        error: ErrorResponse = kwargs["error"]
-        logger.warning(f"{self} connection error, will retry: {error}")
-        await self.stop_all_metrics()
-        # NOTE(aleix): we don't disconnect (i.e. call finish on the connection)
-        # because this triggers more errors internally in the Deepgram SDK. So,
-        # we just forget about the previous connection and create a new one.
-        await self._connect()
-
    async def _on_speech_started(self, *args, **kwargs):
        await self.start_metrics()
        await self._call_event_handler("on_speech_started", *args, **kwargs)
--- a/src/pipecat/services/openai.py
+++ b/src/pipecat/services/openai.py
@@ -266,6 +266,7 @@ class BaseOpenAILLMService(LLMService):
                if tool_call.function and tool_call.function.name:
                    function_name += tool_call.function.name
                    tool_call_id = tool_call.id
+                    await self.call_start_function(context, function_name)
                if tool_call.function and tool_call.function.arguments:
                    # Keep iterating through the response to collect all the argument fragments
                    arguments += tool_call.function.arguments
--- a/src/pipecat/services/websocket_service.py
+++ b/src/pipecat/services/websocket_service.py
@@ -13,7 +13,6 @@ from loguru import logger
 from websockets.protocol import State

 from pipecat.frames.frames import ErrorFrame
-from pipecat.utils.network import exponential_backoff_time


 class WebsocketService(ABC):
@@ -52,6 +51,27 @@ class WebsocketService(ABC):
        await self._connect_websocket()
        return await self._verify_connection()

+    def _calculate_wait_time(
+        self, attempt: int, min_wait: float = 4, max_wait: float = 10, multiplier: float = 1
+    ) -> float:
+        """Calculate exponential backoff wait time.
+
+        Args:
+            attempt: Current attempt number (1-based)
+            min_wait: Minimum wait time in seconds
+            max_wait: Maximum wait time in seconds
+            multiplier: Base multiplier for exponential calculation
+
+        Returns:
+            Wait time in seconds
+        """
+        try:
+            exp = 2 ** (attempt - 1) * multiplier
+            result = max(0, min(exp, max_wait))
+            return max(min_wait, result)
+        except (ValueError, ArithmeticError):
+            return max_wait
+
    async def _receive_task_handler(self, report_error: Callable[[ErrorFrame], Awaitable[None]]):
        """Handles WebSocket message receiving with automatic retry logic.

@@ -84,7 +104,7 @@ class WebsocketService(ABC):
                try:
                    if await self._reconnect_websocket(retry_count):
                        retry_count = 0  # Reset counter on successful reconnection
-                    wait_time = exponential_backoff_time(retry_count)
+                    wait_time = self._calculate_wait_time(retry_count)
                    await asyncio.sleep(wait_time)
                except Exception as reconnect_error:
                    logger.error(f"{self} reconnection failed: {reconnect_error}")
--- a/src/pipecat/transports/services/daily.py
+++ b/src/pipecat/transports/services/daily.py
@@ -329,10 +329,6 @@ class DailyTransportClient(EventHandler):
    def _speaker_name(self):
        return f"speaker-{self}"

-    @property
-    def room_url(self) -> str:
-        return self._room_url
-
    @property
    def participant_id(self) -> str:
        return self._participant_id
@@ -1116,10 +1112,6 @@ class DailyTransport(BaseTransport):
    # DailyTransport
    #

-    @property
-    def room_url(self) -> str:
-        return self._client.room_url
-
    @property
    def participant_id(self) -> str:
        return self._client.participant_id
--- a/src/pipecat/utils/network.py
+++ b/src/pipecat/utils/network.py
@@ -1,27 +0,0 @@
-#
-# Copyright (c) 2024–2025, Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-
-def exponential_backoff_time(
-    attempt: int, min_wait: float = 4, max_wait: float = 10, multiplier: float = 1
-) -> float:
-    """Calculate exponential backoff wait time.
-
-    Args:
-        attempt: Current attempt number (1-based)
-        min_wait: Minimum wait time in seconds
-        max_wait: Maximum wait time in seconds
-        multiplier: Base multiplier for exponential calculation
-
-    Returns:
-        Wait time in seconds
-    """
-    try:
-        exp = 2 ** (attempt - 1) * multiplier
-        result = max(0, min(exp, max_wait))
-        return max(min_wait, result)
-    except (ValueError, ArithmeticError):
-        return max_wait
--- a/tests/test_stt_mute_filter.py
+++ b/tests/test_stt_mute_filter.py
@@ -11,13 +11,12 @@ from pipecat.frames.frames import (
    BotStoppedSpeakingFrame,
    FunctionCallInProgressFrame,
    FunctionCallResultFrame,
-    InputAudioRawFrame,
    STTMuteFrame,
    UserStartedSpeakingFrame,
    UserStoppedSpeakingFrame,
 )
 from pipecat.processors.filters.stt_mute_filter import STTMuteConfig, STTMuteFilter, STTMuteStrategy
-from pipecat.tests.utils import SleepFrame, run_test
+from pipecat.tests.utils import run_test


 class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
@@ -27,14 +26,10 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
        frames_to_send = [
            BotStartedSpeakingFrame(),  # First bot speech starts
            UserStartedSpeakingFrame(),  # Should be suppressed
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed
            UserStoppedSpeakingFrame(),  # Should be suppressed
            BotStoppedSpeakingFrame(),  # First bot speech ends
            BotStartedSpeakingFrame(),  # Second bot speech
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
            BotStoppedSpeakingFrame(),
        ]
@@ -46,7 +41,6 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
            STTMuteFrame,  # mute=False
            BotStartedSpeakingFrame,
            UserStartedSpeakingFrame,  # Now passes through
-            InputAudioRawFrame,  # Now passes through
            UserStoppedSpeakingFrame,  # Now passes through
            BotStoppedSpeakingFrame,
        ]
@@ -63,19 +57,12 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
        frames_to_send = [
            BotStartedSpeakingFrame(),  # First speech starts
            UserStartedSpeakingFrame(),  # Should be suppressed
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed
            UserStoppedSpeakingFrame(),  # Should be suppressed
            BotStoppedSpeakingFrame(),  # First speech ends
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
            BotStartedSpeakingFrame(),  # Second speech starts
            UserStartedSpeakingFrame(),  # Should be suppressed again
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed again
            UserStoppedSpeakingFrame(),  # Should be suppressed again
            BotStoppedSpeakingFrame(),  # Second speech ends
        ]
@@ -86,7 +73,6 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
            BotStoppedSpeakingFrame,
            STTMuteFrame,  # mute=False
            UserStartedSpeakingFrame,
-            InputAudioRawFrame,
            UserStoppedSpeakingFrame,
            BotStartedSpeakingFrame,
            STTMuteFrame,  # mute=True
@@ -148,23 +134,15 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):

        frames_to_send = [
            UserStartedSpeakingFrame(),  # Should be suppressed (starts muted)
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed
            UserStoppedSpeakingFrame(),  # Should be suppressed
            BotStartedSpeakingFrame(),  # First bot speech
            UserStartedSpeakingFrame(),  # Should be suppressed
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed
            UserStoppedSpeakingFrame(),  # Should be suppressed
            BotStoppedSpeakingFrame(),  # First speech ends, unmutes
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
            BotStartedSpeakingFrame(),  # Second speech
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
            BotStoppedSpeakingFrame(),
        ]
@@ -175,11 +153,9 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):
            BotStoppedSpeakingFrame,
            STTMuteFrame,  # mute=False after first speech
            UserStartedSpeakingFrame,
-            InputAudioRawFrame,
            UserStoppedSpeakingFrame,
            BotStartedSpeakingFrame,
            UserStartedSpeakingFrame,
-            InputAudioRawFrame,
            UserStoppedSpeakingFrame,
            BotStoppedSpeakingFrame,
        ]
@@ -214,30 +190,23 @@ class TestSTTMuteFilter(unittest.IsolatedAsyncioTestCase):

        frames_to_send = [
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
            BotStartedSpeakingFrame(),  # Bot starts speaking
            UserStartedSpeakingFrame(),  # Should be suppressed
-            InputAudioRawFrame(
-                audio=b"", sample_rate=16000, num_channels=1
-            ),  # Should be suppressed
            UserStoppedSpeakingFrame(),  # Should be suppressed
            BotStoppedSpeakingFrame(),  # Bot stops speaking
            UserStartedSpeakingFrame(),  # Should pass through
-            InputAudioRawFrame(audio=b"", sample_rate=16000, num_channels=1),  # Should pass through
            UserStoppedSpeakingFrame(),  # Should pass through
        ]

        expected_returned_frames = [
            UserStartedSpeakingFrame,
-            InputAudioRawFrame,
            UserStoppedSpeakingFrame,
            BotStartedSpeakingFrame,
            STTMuteFrame,  # mute=True
            BotStoppedSpeakingFrame,
            STTMuteFrame,  # mute=False
            UserStartedSpeakingFrame,
-            InputAudioRawFrame,
            UserStoppedSpeakingFrame,
        ]

--- a/tests/test_utils_network.py
+++ b/tests/test_utils_network.py
@@ -1,34 +0,0 @@
-#
-# Copyright (c) 2024-2025 Daily
-#
-# SPDX-License-Identifier: BSD 2-Clause License
-#
-
-import unittest
-
-from pipecat.utils.network import exponential_backoff_time
-
-
-class TestUtilsNetwork(unittest.IsolatedAsyncioTestCase):
-    async def test_exponential_backoff_time(self):
-        # min_wait=4, max_wait=10, multiplier=1
-        assert exponential_backoff_time(attempt=1, min_wait=4, max_wait=10, multiplier=1) == 4
-        assert exponential_backoff_time(attempt=2, min_wait=4, max_wait=10, multiplier=1) == 4
-        assert exponential_backoff_time(attempt=3, min_wait=4, max_wait=10, multiplier=1) == 4
-        assert exponential_backoff_time(attempt=4, min_wait=4, max_wait=10, multiplier=1) == 8
-        assert exponential_backoff_time(attempt=5, min_wait=4, max_wait=10, multiplier=1) == 10
-        assert exponential_backoff_time(attempt=6, min_wait=4, max_wait=10, multiplier=1) == 10
-        # min_wait=1, max_wait=10, multiplier=1
-        assert exponential_backoff_time(attempt=1, min_wait=1, max_wait=10, multiplier=1) == 1
-        assert exponential_backoff_time(attempt=2, min_wait=1, max_wait=10, multiplier=1) == 2
-        assert exponential_backoff_time(attempt=3, min_wait=1, max_wait=10, multiplier=1) == 4
-        assert exponential_backoff_time(attempt=4, min_wait=1, max_wait=10, multiplier=1) == 8
-        assert exponential_backoff_time(attempt=5, min_wait=1, max_wait=10, multiplier=1) == 10
-        assert exponential_backoff_time(attempt=6, min_wait=1, max_wait=10, multiplier=1) == 10
-        # min_wait=1, max_wait=20, multiplier=2
-        assert exponential_backoff_time(attempt=1, min_wait=1, max_wait=20, multiplier=2) == 2
-        assert exponential_backoff_time(attempt=2, min_wait=1, max_wait=20, multiplier=2) == 4
-        assert exponential_backoff_time(attempt=3, min_wait=1, max_wait=20, multiplier=2) == 8
-        assert exponential_backoff_time(attempt=4, min_wait=1, max_wait=20, multiplier=2) == 16
-        assert exponential_backoff_time(attempt=5, min_wait=1, max_wait=20, multiplier=2) == 20
-        assert exponential_backoff_time(attempt=6, min_wait=1, max_wait=20, multiplier=2) == 20