Starstruk Logo MarkStarstruk

v0.0.90

pipecat-ai/pipecatv0.0.90Oct 10, 2025by aconchillo

AI Summary

Added KrispVivaFilter audio filter, folder download support from runner, GeminiLiveVertexLLMService for Google Vertex AI, new GeminiLiveLLMService configuration options (thinking, enable_affective_dialog, proactivity), pipeline error event, and OpenAI service_tier parameter for latency control.

Key Highlights

  • KrispVivaFilter audio filter using Krisp VIVA SDK
  • Folder download support via --folder argument
  • GeminiLiveVertexLLMService for accessing Gemini Live via Vertex AI
  • New GeminiLiveLLMService configuration options
  • on_pipeline_error event for PipelineTask

New Features

  • KrispVivaFilter audio filter
  • Folder download support via --folder argument
  • GeminiLiveVertexLLMService
  • GeminiLiveLLMService thinking configuration
  • GeminiLiveLLMService enable_affective_dialog option
  • GeminiLiveLLMService proactivity option
  • on_pipeline_error event for PipelineTask
  • service_tier InputParam for BaseOpenAILLMService

Full Release Notes

### Added

- Added audio filter `KrispVivaFilter` using the Krisp VIVA SDK.

- Added `--folder` argument to the runner, allowing files saved in that folder to be downloaded from `http://HOST:PORT/file/FILE`.

- Added `GeminiLiveVertexLLMService`, for accessing Gemini Live via Google Vertex AI.

- Added some new configuration options to `GeminiLiveLLMService`:

  - `thinking`
  - `enable_affective_dialog`
  - `proactivity`

  Note that these new configuration options require using a newer model than the default, like "gemini-2.5-flash-native-audio-preview-09-2025". The last two require specifying `http_options=HttpOptions(api_version="v1alpha")`.

- Added `on_pipeline_error` event to `PipelineTask`. This event will get fired when an `ErrorFrame` is pushed (use `FrameProcessor.push_error()`).

  ```python
  @task.event_handler("on_pipeline_error")
  async def on_pipeline_error(task: PipelineTask, frame: ErrorFrame):
      ...
  ```

- Added a `service_tier` `InputParam` to the `BaseOpenAILLMService`. This parameter can influence the latency of the response. For example `"priority"` will result in faster completions, but in exchange for a higher price.

### Changed

- Updated `GeminiLiveLLMService` to use the `google-genai` library rather than use WebSockets directly.

### Deprecated

- `LivekitFrameSerializer` is now deprecated. Use `LiveKitTransport` instead.

- `pipecat.service.openai_realtime` is now deprecated, use `pipecat.services.openai.realtime` instead or `pipecat.services.azure.realtime` for Azure Realtime.

- `pipecat.service.aws_nova_sonic` is now deprecated, use `pipecat.services.aws.nova_sonic` instead.

- `GeminiMultimodalLiveLLMService` is now deprecated, use `GeminiLiveLLMService`.

### Fixed

- Fixed a `GoogleVertexLLMService` issue that would generate an error if no token information was returned.

- `GeminiLiveLLMService` will now end gracefully (i.e. after the bot has finished) upon receiving an `EndFrame`.

- `GeminiLiveLLMService` will try to seamlessly reconnect when it loses its connection.