dv-pipecat-ai 0.0.82.dev816__tar.gz → 0.0.82.dev857__tar.gz

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/CHANGELOG.md

@@ -5,6 +5,353 @@ 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).
 
+## [0.0.84] - 2025-09-05
+
+### Added
+
+- Add the ability to send DTMF to `LiveKitTransport`.
+
+- Expanded support for universal `LLMContext` to the Anthropic LLM service.
+  Using the universal `LLMContext` and associated `LLMContextAggregatorPair` is
+  a pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
+
+### Changed
+
+- Updated `daily-python` to 0.19.9.
+
+- Restored `DailyTransport`'s native DTMF support using Daily's `send_dtmf()`
+  method instead of generated audio tones.
+
+### Fixed
+
+- Fixed a `AWSBedrockLLMService` crash caused by an extra `await`.
+
+- Fixed a `OpenAIImageGenService` issue where it was not creating
+  `URLImageRawFrame` correctly.
+
+## [0.0.83] - 2025-09-03
+
+### Added
+
+- Added multilingual support for AsyncAI in `AsyncAITTSService` and `AsyncAIHttpTTSService`.
+
+  - New `languages`: `es`, `fr`, `de`, `it`.
+
+- Added new frames `InputTransportMessageUrgentFrame` and
+  `DailyInputTransportMessageUrgentFrame` for transport messages received from
+  external sources.
+
+- Added `UserSpeakingFrame`. This will be sent upstream and downstream while VAD
+  detects the user is speaking.
+
+- Expanded support for universal `LLMContext` to more LLM services. Using the
+  universal `LLMContext` and associated `LLMContextAggregatorPair` is a
+  pre-requisite for using `LLMSwitcher` to switch between LLMs at runtime.
+  Here are the newly-supported services:
+
+  - Azure
+  - Cerebras
+  - Deepseek
+  - Fireworks AI
+  - Google Vertex AI
+  - Grok
+  - Groq
+  - Mistral
+  - NVIDIA NIM
+  - Ollama
+  - OpenPipe
+  - OpenRouter
+  - Perplexity
+  - Qwen
+  - SambaNova
+  - Together.ai
+
+- Added support for WhatsApp User-initiated Calls.
+
+- Added new audio filter `AICFilter`, speech enhancement for improving VAD/STT
+  performance, no ONNX dependency.
+  See https://ai-coustics.com/sdk/
+
+- Added a timeout around cancel input tasks to prevent indefinite hangs when
+  cancellation is swallowed by third-party code.
+
+- Added `pipecat.extensions.ivr` for automated IVR system navigation with
+  configurable goals and conversation handling. Supports DTMF input, verbal
+  responses, and intelligent menu traversal.
+
+  Basic usage:
+
+  ```python
+  from pipecat.extensions.ivr.ivr_navigator import IVRNavigator
+
+  # Create IVR navigator with your goal
+  ivr_navigator = IVRNavigator(
+      llm=llm_service,
+      ivr_prompt="Navigate to billing department to dispute a charge"
+  )
+
+  # Handle different outcomes
+  @ivr_navigator.event_handler("on_conversation_detected")
+  async def on_conversation(processor, conversation_history):
+      # Switch to normal conversation mode
+      pass
+
+  @ivr_navigator.event_handler("on_ivr_status_changed")
+  async def on_ivr_status(processor, status):
+      if status == IVRStatus.COMPLETED:
+          # End pipeline, transfer call, or start bot conversation
+      elif status == IVRStatus.STUCK:
+          # Handle navigation failure
+  ```
+
+- `BaseOutputTransport` now implements `write_dtmf()` by loading DTMF audio and
+  sending it through the transport. This makes sending DTMF generic across all
+  output transports.
+
+- Added new config parameters to `GladiaSTTService`.
+  - PreProcessingConfig > `audio_enhancer` to enhance audio quality.
+  - CustomVocabularyItem > `pronunciations` and `language` to specify special
+    pronunciations and in which language it will be pronounced.
+
+### Changed
+
+- `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` are also pushed
+  upstream.
+
+- `ParallelPipeline` now waits for `CancelFrame` to finish in all branches
+  before pushing it downstream.
+
+- Added `sip_codecs` to the `DailyRoomSipParams`.
+
+- Updated the `configure()` function in `pipecat.runner.daily` to include new
+  args to create SIP-enabled rooms. Additionally, added new args to control the
+  room and token expiration durations.
+
+- `pipecat.frames.frames.KeypadEntry` is deprecated and has been moved to
+  `pipecat.audio.dtmf.types.KeypadEntry`.
+
+- Updated `RimeTTSService`'s flush_audio message to conform with Rime's official
+  API.
+
+- Updated the default model for `CerebrasLLMService` to GPT-OSS-120B.
+
+### Removed
+
+- Remove `StopInterruptionFrame`. This was a legacy frame that was not being
+  used really anywhere and it didn't provide any useful meaning. It was only
+  pushed after `UserStoppedSpeakingFrame`, so developers can just use
+  `UserStoppedSpeakingFrame`.
+
+- `DailyTransport.write_dtmf()` has been removed in favor of the generic
+  `BaseOutputTransport.write_dtmf()`.
+
+- Remove deprecated `DailyTransport.send_dtmf()`.
+
+### Deprecated
+
+- Transports have been re-organized.
+
+  ```
+  pipecat.transports.network.small_webrtc        -> pipecat.transports.smallwebrtc.transport
+  pipecat.transports.network.webrtc_connection   -> pipecat.transports.smallwebrtc.connection
+  pipecat.transports.network.websocket_client    -> pipecat.transports.websocket.client
+  pipecat.transports.network.websocket_server    -> pipecat.transports.websocket.server
+  pipecat.transports.network.fastapi_websocket   -> pipecat.transports.websocket.fastapi
+  pipecat.transports.services.daily              -> pipecat.transports.daily.transport
+  pipecat.transports.services.helpers.daily_rest -> pipecat.transports.daily.utils
+  pipecat.transports.services.livekit            -> pipecat.transports.livekit.transport
+  pipecat.transports.services.tavus              -> pipecat.transports.tavus.transport
+  ```
+
+- `pipecat.frames.frames.KeypadEntry` is deprecated use
+  `pipecat.audio.dtmf.types.KeypadEntry` instead.
+
+### Fixed
+
+- Fixed an issue where messages received from the transport were always being resent.
+
+- Fixed `SmallWebRTCTransport` to not use `mid` to decide if the transceiver should
+  be `sendrecv` or not.
+
+- Fixed an issue where Deepgram swallowed `asyncio.CancelledError` during
+  disconnect, preventing tasks from being cancelled.
+
+- Fixed an issue where `PipelineTask` was not cleaning up the observers.
+
+### Performance
+
+- Reduced latency and improved memory performance in `Mem0MemoryService`.
+
+## [0.0.82] - 2025-08-28
+
+### Added
+
+- Added a new `LLMRunFrame` to trigger an LLM response:
+
+  ```python
+  await task.queue_frames([LLMRunFrame()])
+  ```
+
+  This replaces `OpenAILLMContextFrame`, which you’d previously typically use
+  like this:
+
+  ```python
+  await task.queue_frames([context_aggregator.user().get_context_frame()])
+  ```
+
+  Use this way of kicking off your conversation when you’ve already initialized
+  your context and are simply instructing the bot when to go:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+
+  # ...
+
+  @transport.event_handler("on_client_connected")
+  async def on_client_connected(transport, client):
+      # Kick off the conversation.
+      await task.queue_frames([LLMRunFrame()])
+  ```
+
+  Note that if you want to add new messages when kicking off the conversation,
+  you could use `LLMMessagesAppendFrame` with `run_llm=True` instead:
+
+  ```python
+  @transport.event_handler("on_client_connected")
+  async def on_client_connected(transport, client):
+      # Kick off the conversation.
+      await task.queue_frames([LLMMessagesAppendFrame(new_messages, run_llm=True)])
+  ```
+
+  In the rare case you don’t have a context aggregator in your pipeline, then
+  you may continue using a context frame.
+
+- Added support for switching between audio+text to text-only modes within the
+  same pipeline. This is done by pushing
+  `LLMConfigureOutputFrame(skip_tts=True)` to enter text-only mode, and
+  disabling it to return to audio+text. The LLM will still generate tokens and
+  add them to the context, but they will not be sent to TTS.
+
+- Added `skip_tts` field to `TextFrame`. This lets a text frame bypass TTS while
+  still being included in the LLM context. Useful for cases like structured text
+  that isn’t meant to be spoken but should still contribute to context.
+
+- Added a `cancel_timeout_secs` argument to `PipelineTask` which defines how
+  long the pipeline has to complete cancellation. When `PipelineTask.cancel()`
+  is called, a `CancelFrame` is pushed through the pipeline and must reach the
+  end. If it does not reach the end within the specified time, a warning is
+  shown and the wait is aborted.
+
+- Added a new "universal" (LLM-agnostic) `LLMContext` and accompanying
+  `LLMContextAggregatorPair`, which will eventually replace `OpenAILLMContext`
+  (and the other under-the-hood contexts) and the other context aggregators.
+  The new universal `LLMContext` machinery allows a single context to be shared
+  between different LLMs, enabling runtime LLM switching and scenarios like
+  failover.
+
+  From the developer's point of view, switching to using the new universal
+  context machinery will usually be a matter of going from this:
+
+  ```python
+  context = OpenAILLMContext(messages, tools)
+  context_aggregator = llm.create_context_aggregator(context)
+  ```
+
+  To this:
+
+  ```python
+  context = LLMContext(messages, tools)
+  context_aggregator = LLMContextAggregatorPair(context)
+  ```
+
+  To start, the universal `LLMContext` is supported with the following LLM
+  services:
+
+  - `OpenAILLMService`
+  - `GoogleLLMService`
+
+- Added a new `LLMSwitcher` class to enable runtime LLM switching, built atop a
+  new generic `ServiceSwitcher`.
+
+  Switchers take a switching strategy. The first available strategy is
+  `ServiceSwitcherStrategyManual`.
+
+  To switch LLMs at runtime, the LLMs must be sharing one instance of the new
+  universal `LLMContext` (see above bullet).
+
+  ```python
+  # Instantiate your LLM services
+  llm_openai = OpenAILLMService(api_key=os.getenv("OPENAI_API_KEY"))
+  llm_google = GoogleLLMService(api_key=os.getenv("GOOGLE_API_KEY"))
+
+  # Instantiate a switcher
+  # (ServiceSwitcherStrategyManual defaults to OpenAI, as it's first in the list)
+  llm_switcher = LLMSwitcher(
+      llms=[llm_openai, llm_google], strategy_type=ServiceSwitcherStrategyManual
+  )
+
+  # Create your pipeline
+  pipeline = Pipeline(
+    [
+        transport.input(),
+        stt,
+        context_aggregator.user(),
+        llm_switcher,
+        tts,
+        transport.output(),
+        context_aggregator.assistant(),
+    ]
+  )
+  task = PipelineTask(pipeline, params=PipelineParams(allow_interruptions=True))
+
+  # ...
+  # Whenever is appropriate, switch LLMs!
+  await task.queue_frames([ManuallySwitchServiceFrame(service=llm_google)])
+  ```
+
+- Added an `LLMService.run_inference()` method to LLM services to enable
+  direct, out-of-band (i.e. out-of-pipeline) inference.
+
+### Changed
+
+- Updated `daily-python` to 0.19.8.
+
+- `PipelineTask` now waits for `StartFrame` to reach the end of the pipeline
+  before pushing any other frames.
+
+- Updated `CartesiaTTSService` and `CartesiaHttpTTSService` to align with
+  Cartesia's changes for the `speed` parameter. It now takes only an enum of
+  `slow`, `normal`, or `fast`.
+
+- Added support to `AWSBedrockLLMService` for setting authentication
+  credentials through environment variables.
+
+- Updated `SarvamTTSService` to use WebSocket streaming for real-time audio
+  generation with multiple Indian languages, with HTTP support still available
+  via `SarvamHttpTTSService`.
+
+### Fixed
+
+- Fixed an RTVI issue that was causing frames to be pushed before pipeline was
+  properly initialized.
+
+- Fixed some `get_messages_for_logging()` that were returning a JSON string
+  instead of a list.
+
+- Fixed a `DailyTransport` issue that prevented DTMF tones from being sent.
+
+- Fixed a missing import in `SentryMetrics`.
+
+- Fixed `AWSPollyTTSService` to support AWS credential provider chain (IAM
+  roles, IRSA, instance profiles) instead of requiring explicit environment
+  variables.
+
+- Fixed a `CartesiaTTSService` issue that was causing the application to hang
+  after Cartesia's 5 minutes timed out.
+
+- Fixed an issue preventing `SpeechmaticsSTTService` from transcribing audio.
+
 ## [0.0.81] - 2025-08-25
 
 ### Added
@@ -54,8 +401,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ### Deprecated
 
-- `FrameProcessor.wait_for_task()` is deprecated. Use `await task` or `await
-  asyncio.wait_for(task, timeout)` instead.
+- `FrameProcessor.wait_for_task()` is deprecated. Use `await task` or
+  `await asyncio.wait_for(task, timeout)` instead.
 
 ### Removed
 

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/CLAUDE.md

@@ -60,6 +60,25 @@ python scripts/version-utils.py update 0.0.75.dev123  # Manual version update
 
 See **[docs/AUTO_RELEASE.md](docs/AUTO_RELEASE.md)** for complete documentation.
 
+## Recent Releases
+
+### [0.0.84] - 2025-09-05
+**Major Updates:**
+- **DTMF Support**: Added DTMF capabilities to `LiveKitTransport` and restored native DTMF for `DailyTransport`
+- **Universal LLM Context**: Expanded support for universal `LLMContext` to Anthropic, enabling LLM switching at runtime
+- **Performance**: Updated `daily-python` to 0.19.9
+- **Bug Fixes**: Fixed `AWSBedrockLLMService` crash and `OpenAIImageGenService` frame creation issues
+
+### [0.0.83] - 2025-09-03
+**Major Features:**
+- **Multilingual TTS**: AsyncAI TTS with support for Spanish, French, German, Italian
+- **Enhanced Frame System**: New `InputTransportMessageUrgentFrame`, `DailyInputTransportMessageUrgentFrame`, and `UserSpeakingFrame`
+- **Universal LLM Support**: Extended to 15+ services (Azure, Cerebras, Deepseek, Fireworks AI, Google Vertex AI, Grok, Groq, Mistral, NVIDIA NIM, Ollama, OpenPipe, OpenRouter, Perplexity, Qwen, SambaNova, Together.ai)
+- **WhatsApp Integration**: Support for WhatsApp user-initiated calls
+- **IVR Navigator**: New `pipecat.extensions.ivr` for automated IVR system navigation
+- **Audio Enhancement**: `AICFilter` for speech enhancement without ONNX dependency
+- **DTMF Processing**: Generic DTMF audio loading across all output transports
+
 ### Ringg Chatbot Development (Primary Codebase)
 The main development work happens in `examples/ringg-chatbot/`, which is a production telephony chatbot system.
 
@@ -113,9 +132,12 @@ Pipecat is a **pipeline-based real-time AI conversation framework** for building
 ### AI Services Integration
 - **AIService** base class with common functionality
 - **LLMService**, **STTService**, **TTSService**, **VisionService** for different AI capabilities
+- **Universal LLMContext**: LLM-agnostic context enabling runtime LLM switching
+- **LLMSwitcher**: Runtime switching between different LLM services
+- **LLMContextAggregatorPair**: Universal context aggregator for cross-LLM compatibility
 - Context aggregators manage conversation state
 - Function calling support with result callbacks
-- Multiple providers: OpenAI, Anthropic, Google, AWS, Azure, Deepgram, ElevenLabs, etc.
+- Multiple providers: OpenAI, Anthropic, Google, AWS, Azure, Deepgram, ElevenLabs, AsyncAI, etc.
 
 ### Transport Layer
 - **BaseTransport** provides input/output interface
@@ -138,18 +160,20 @@ AssemblyAI, AWS Transcribe, Azure, Cartesia, Deepgram, Fal Wizper, Gladia, Googl
 Anthropic, AWS Bedrock, Azure, Cerebras, DeepSeek, Fireworks AI, Google Gemini/Vertex AI, Grok, Groq, NVIDIA NIM, Ollama, OpenAI, OpenPipe, OpenRouter, Perplexity, Qwen, SambaNova, Together AI
 
 ### Text-to-Speech (TTS)
-AWS Polly, Azure, Cartesia, Deepgram, ElevenLabs, Fish, Google, Groq, LMNT, MiniMax, Neuphonic, NVIDIA Riva, OpenAI, Piper, PlayHT, Rime, Sarvam, XTTS
+AsyncAI, AWS Polly, Azure, Cartesia, Deepgram, ElevenLabs, Fish, Google, Groq, LMNT, MiniMax, Neuphonic, NVIDIA Riva, OpenAI, Piper, PlayHT, Rime, Sarvam, XTTS
 
 ### Transport & Communication
-Daily (WebRTC), SmallWebRTC, FastAPI WebSocket, WebSocket Server, Tavus
+Daily (WebRTC), SmallWebRTC, FastAPI WebSocket, WebSocket Server, Tavus, WhatsApp
 
 ### Additional Services
 - **Speech-to-Speech**: AWS Nova Sonic, Gemini, OpenAI
 - **Image Generation**: fal, Google Imagen, OpenAI
-- **Video**: Simli, Tavus
+- **Video**: HeyGen, Simli, Tavus
 - **Memory**: Mem0
 - **Vision**: Moondream
 - **Analytics**: Sentry
+- **IVR Navigation**: Automated IVR system navigation with DTMF and voice response
+- **Audio Enhancement**: AICoustics filter for VAD/STT performance improvement
 
 ## Typical Data Flow Pattern
 
@@ -174,15 +198,21 @@ Based on Pipecat documentation, key frame types include:
   - Subclasses: `InputAudioRawFrame`, `OutputAudioRawFrame`, `TTSAudioRawFrame`
 - **ImageRawFrame**: Image data with `size` and `format`
   - Subclasses: `InputImageRawFrame`, `VisionImageRawFrame`, `URLImageRawFrame`
-- **TextFrame**: Text chunks for processing
+- **TextFrame**: Text chunks for processing (supports `skip_tts` field)
 - **TranscriptionFrame**: Speech transcriptions with `user_id`, `timestamp`, `language`
-- **LLMMessagesFrame**: Message arrays for LLM processing
+- **LLMMessagesFrame**: Message arrays for LLM processing (deprecated, use `LLMMessagesUpdateFrame`)
+- **InputTransportMessageUrgentFrame**: Urgent transport messages from external sources
+- **DailyInputTransportMessageUrgentFrame**: Daily-specific urgent transport messages
+- **UserSpeakingFrame**: Bidirectional frame sent while VAD detects user speaking
+- **LLMRunFrame**: Trigger LLM response without context changes
 
 ### System Control
 - **StartFrame/EndFrame**: Pipeline lifecycle control
-- **StartInterruptionFrame/StopInterruptionFrame**: User speech interruption handling
+- **StartInterruptionFrame**: User speech interruption handling (StopInterruptionFrame removed in v0.0.83)
 - **BotStartedSpeakingFrame/BotStoppedSpeakingFrame**: Bot speech activity
 - **FunctionCallInProgressFrame/FunctionCallResultFrame**: LLM function calling
+- **LLMConfigureOutputFrame**: Configure LLM output behavior (e.g., `skip_tts=True` for text-only mode)
+- **ManuallySwitchServiceFrame**: Switch between services at runtime (used with LLMSwitcher)
 
 ## Common Development Patterns
 
@@ -206,6 +236,21 @@ task = PipelineTask(pipeline)
 await task.run()
 ```
 
+### Runtime LLM Switching
+```python
+# Using Universal LLMContext and LLMSwitcher
+context = LLMContext(messages, tools)  # Universal context
+context_aggregator = LLMContextAggregatorPair(context)
+
+# Create LLM switcher with multiple providers
+llm_openai = OpenAILLMService(api_key=openai_key)
+llm_anthropic = AnthropicLLMService(api_key=anthropic_key)
+llm_switcher = LLMSwitcher([llm_openai, llm_anthropic])
+
+# Switch LLMs at runtime
+await task.queue_frames([ManuallySwitchServiceFrame(service=llm_anthropic)])
+```
+
 ### Adding New Frame Types
 - Define in `src/pipecat/frames/frames.py`
 - Extend appropriate base frame class

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dv-pipecat-ai
-Version: 0.0.82.dev816
+Version: 0.0.82.dev857
 Summary: An open source framework for voice (and multimodal) assistants
 License-Expression: BSD-2-Clause
 Project-URL: Source, https://github.com/pipecat-ai/pipecat
@@ -15,6 +15,7 @@ Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
 License-File: LICENSE
+Requires-Dist: aiofiles<25,>=24.1.0
 Requires-Dist: aiohttp<4,>=3.11.12
 Requires-Dist: audioop-lts~=0.2.1; python_version >= "3.13"
 Requires-Dist: docstring_parser~=0.16
@@ -31,6 +32,8 @@ Requires-Dist: soxr~=0.5.0
 Requires-Dist: openai<=1.99.1,>=1.74.0
 Requires-Dist: numba==0.61.2
 Requires-Dist: wait_for2>=0.4.1; python_version < "3.12"
+Provides-Extra: aic
+Requires-Dist: aic-sdk~=1.0.1; extra == "aic"
 Provides-Extra: anthropic
 Requires-Dist: anthropic~=0.49.0; extra == "anthropic"
 Provides-Extra: assemblyai
@@ -50,7 +53,7 @@ Requires-Dist: websockets<15.0,>=13.1; extra == "cartesia"
 Provides-Extra: cerebras
 Provides-Extra: deepseek
 Provides-Extra: daily
-Requires-Dist: daily-python~=0.19.7; extra == "daily"
+Requires-Dist: daily-python~=0.19.9; extra == "daily"
 Provides-Extra: deepgram
 Requires-Dist: deepgram-sdk~=4.7.0; extra == "deepgram"
 Provides-Extra: elevenlabs
@@ -130,6 +133,8 @@ Requires-Dist: uvicorn<1.0.0,>=0.32.0; extra == "runner"
 Requires-Dist: fastapi<0.117.0,>=0.115.6; extra == "runner"
 Requires-Dist: pipecat-ai-small-webrtc-prebuilt>=1.0.0; extra == "runner"
 Provides-Extra: sambanova
+Provides-Extra: sarvam
+Requires-Dist: websockets<15.0,>=13.1; extra == "sarvam"
 Provides-Extra: sentry
 Requires-Dist: sentry-sdk~=2.23.1; extra == "sentry"
 Provides-Extra: local-smart-turn
@@ -231,7 +236,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 | Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
 | Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/README.md

@@ -62,7 +62,7 @@ You can connect to Pipecat from any platform using our official SDKs:
 | Video               | [HeyGen](https://docs.pipecat.ai/server/services/video/heygen), [Tavus](https://docs.pipecat.ai/server/services/video/tavus), [Simli](https://docs.pipecat.ai/server/services/video/simli)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                            |
 | Memory              | [mem0](https://docs.pipecat.ai/server/services/memory/mem0)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 | Vision & Image      | [fal](https://docs.pipecat.ai/server/services/image-generation/fal), [Google Imagen](https://docs.pipecat.ai/server/services/image-generation/fal), [Moondream](https://docs.pipecat.ai/server/services/vision/moondream)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                             |
-| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                        |
+| Audio Processing    | [Silero VAD](https://docs.pipecat.ai/server/utilities/audio/silero-vad-analyzer), [Krisp](https://docs.pipecat.ai/server/utilities/audio/krisp-filter), [Koala](https://docs.pipecat.ai/server/utilities/audio/koala-filter), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter), [Noisereduce](https://docs.pipecat.ai/server/utilities/audio/noisereduce-filter)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                              |
 | Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry)                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                           |
 
 📚 [View full services documentation →](https://docs.pipecat.ai/server/services/supported-services)

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/env.example

@@ -1,3 +1,6 @@
+# AI-COUSTICS
+AICOUSTICS_LICENSE_KEY=...
+
 # Anthropic
 ANTHROPIC_API_KEY=...
 
@@ -59,6 +62,9 @@ GOOGLE_VERTEX_TEST_CREDENTIALS=...
 LMNT_API_KEY=...
 LMNT_VOICE_ID=...
 
+# Perplexity
+PERPLEXITY_API_KEY=...
+
 # PlayHT
 PLAY_HT_USER_ID=...
 PLAY_HT_API_KEY=...
@@ -140,3 +146,12 @@ SENTRY_DSN=...
 
 # Heygen
 HEYGEN_API_KEY=...
+
+# Mistral
+MISTRAL_API_KEY=...
+
+# NVIDIA
+NVIDIA_API_KEY=...
+
+# Qwen
+QWEN_API_KEY=...

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/k8s/dv-pipecat/templates/deployment.yaml

@@ -53,6 +53,15 @@ spec:
             {{- toYaml .Values.securityContext | nindent 12 }}
           image: "{{ .Values.image.repository }}:{{ .Values.image.tag | default .Chart.AppVersion }}"
           imagePullPolicy: {{ .Values.image.pullPolicy }}
+          lifecycle:
+            preStop:
+              exec:
+                command:
+                  - /bin/sh
+                  - -c
+                  - >-
+                    wget -q -T 2 -O- http://127.0.0.1:{{ .Values.service.targetPort }}/drain/start || true;
+                    sleep ${PRESTOP_DRAIN_SECONDS:-{{ .Values.preStopDrainSeconds | default 45 }}}
           # Load environment variables from the secret defined in values.yaml
           envFrom:
           - secretRef:
@@ -60,6 +69,8 @@ spec:
           # Define any additional non-secret env vars if needed
           env:
             {{- toYaml .Values.env | nindent 12 }} # Keep using toYaml for the simpler env list
+            - name: PRESTOP_DRAIN_SECONDS
+              value: "{{ .Values.preStopDrainSeconds | default 45 }}"
           ports:
             - name: http
               containerPort: {{ .Values.service.targetPort }}
@@ -69,9 +80,9 @@ spec:
               path: /pc/v1/healthcheck # Updated path
               port: http # Use named port 'http'
             initialDelaySeconds: 60 # Increased delay
-            periodSeconds: 30
+            periodSeconds: 10
             timeoutSeconds: 5
-            failureThreshold: 3
+            failureThreshold: 2
           livenessProbe:
             httpGet:
               path: /pc/v1/healthcheck # Updated path

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/k8s/dv-pipecat/values-prod.yaml

@@ -91,3 +91,11 @@ keda:
   # Production fallback behavior
   failureThreshold: 5 # More tolerant of temporary failures
   fallbackReplicas: 50 # Higher fallback replicas for production
+
+# Pod Disruption Budget for production
+pdb:
+  enabled: true
+  minAvailable: "95%"
+
+# Draining delay for production (seconds)
+preStopDrainSeconds: 60

{dv_pipecat_ai-0.0.82.dev816 → dv_pipecat_ai-0.0.82.dev857}/k8s/dv-pipecat/values-stage.yaml

@@ -84,3 +84,6 @@ keda:
   # Staging fallback behavior
   failureThreshold: 5 # More tolerant of temporary failures
   fallbackReplicas: 1 # Higher fallback replicas for staging
+
+# Draining delay for staging (seconds)
+preStopDrainSeconds: 45