Compare commits
3 Commits
filipi/add
...
hush/TurnT
| Author | SHA1 | Date | |
|---|---|---|---|
|
8bbfa829d3 | ||
|
|
c2eb663bdc | ||
|
|
bf055843e6 |
14
.github/workflows/build.yaml
vendored
14
.github/workflows/build.yaml
vendored
@@ -21,20 +21,20 @@ jobs:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
|
||||
- name: Build project
|
||||
run: uv build
|
||||
|
||||
|
||||
- name: Install project in editable mode
|
||||
run: uv pip install --editable .
|
||||
run: uv pip install --editable .
|
||||
2
.github/workflows/coverage.yaml
vendored
2
.github/workflows/coverage.yaml
vendored
@@ -33,7 +33,7 @@ jobs:
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra websocket
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
- name: Run tests with coverage
|
||||
run: |
|
||||
|
||||
14
.github/workflows/format.yaml
vendored
14
.github/workflows/format.yaml
vendored
@@ -22,22 +22,22 @@ jobs:
|
||||
steps:
|
||||
- name: Checkout repo
|
||||
uses: actions/checkout@v4
|
||||
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v3
|
||||
with:
|
||||
version: "latest"
|
||||
|
||||
|
||||
- name: Set up Python
|
||||
run: uv python install 3.12
|
||||
|
||||
run: uv python install 3.10
|
||||
|
||||
- name: Install development dependencies
|
||||
run: uv sync --group dev
|
||||
|
||||
|
||||
- name: Ruff formatter
|
||||
id: ruff-format
|
||||
run: uv run ruff format --diff
|
||||
|
||||
|
||||
- name: Ruff linter (all rules)
|
||||
id: ruff-check
|
||||
run: uv run ruff check
|
||||
run: uv run ruff check
|
||||
174
.github/workflows/generate-changelog.yml
vendored
174
.github/workflows/generate-changelog.yml
vendored
@@ -1,174 +0,0 @@
|
||||
name: Generate Changelog for Release
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
inputs:
|
||||
version:
|
||||
description: "Release version (e.g., 0.0.97)"
|
||||
required: true
|
||||
type: string
|
||||
date:
|
||||
description: "Release date (YYYY-MM-DD format, defaults to today)"
|
||||
required: false
|
||||
type: string
|
||||
default: ""
|
||||
|
||||
permissions:
|
||||
contents: write
|
||||
pull-requests: write
|
||||
|
||||
jobs:
|
||||
generate-changelog:
|
||||
runs-on: ubuntu-latest
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
with:
|
||||
fetch-depth: 0
|
||||
|
||||
- name: Set up Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
python-version: "3.12"
|
||||
|
||||
- name: Install uv
|
||||
uses: astral-sh/setup-uv@v4
|
||||
with:
|
||||
enable-cache: true
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev
|
||||
|
||||
- name: Set release date
|
||||
id: set_date
|
||||
run: |
|
||||
if [ -z "${{ inputs.date }}" ]; then
|
||||
RELEASE_DATE=$(date +%Y-%m-%d)
|
||||
echo "Using today's date: $RELEASE_DATE"
|
||||
else
|
||||
RELEASE_DATE="${{ inputs.date }}"
|
||||
echo "Using provided date: $RELEASE_DATE"
|
||||
fi
|
||||
echo "release_date=$RELEASE_DATE" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Validate inputs
|
||||
run: |
|
||||
# Validate version format (basic check)
|
||||
if ! [[ "${{ inputs.version }}" =~ ^[0-9]+\.[0-9]+\.[0-9]+.*$ ]]; then
|
||||
echo "Error: Version must be in format X.Y.Z (e.g., 0.0.97)"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate date format if provided
|
||||
if [ -n "${{ inputs.date }}" ]; then
|
||||
if ! date -d "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
# Try macOS date format
|
||||
if ! date -j -f "%Y-%m-%d" "${{ inputs.date }}" >/dev/null 2>&1; then
|
||||
echo "Error: Date must be in YYYY-MM-DD format (e.g., 2025-12-04)"
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
fi
|
||||
|
||||
- name: Check for changelog fragments
|
||||
id: check_fragments
|
||||
run: |
|
||||
FRAGMENT_COUNT=$(find changelog -name "*.md" ! -name "_template.md.j2" | wc -l | tr -d ' ')
|
||||
echo "fragment_count=$FRAGMENT_COUNT" >> $GITHUB_OUTPUT
|
||||
|
||||
if [ "$FRAGMENT_COUNT" -eq "0" ]; then
|
||||
echo "❌ Error: No changelog fragments found in changelog/"
|
||||
echo ""
|
||||
echo "Cannot create a release without changelog entries."
|
||||
echo "Add changelog fragments to the changelog/ directory (e.g., 1234.added.md) and try again."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# Validate fragment types
|
||||
VALID_TYPES="added changed deprecated removed fixed security other"
|
||||
INVALID_FRAGMENTS=""
|
||||
|
||||
for file in changelog/*.md; do
|
||||
# Skip template
|
||||
if [[ "$file" == "changelog/_template.md.j2" ]]; then
|
||||
continue
|
||||
fi
|
||||
|
||||
# Extract type from filename (e.g., 1234.added.md -> added)
|
||||
filename=$(basename "$file")
|
||||
# Handle both 1234.added.md and 1234.added.2.md patterns
|
||||
type=$(echo "$filename" | sed -E 's/^[0-9]+\.([a-z]+)(\.[0-9]+)?\.md$/\1/')
|
||||
|
||||
# Check if type is valid
|
||||
if ! echo "$VALID_TYPES" | grep -wq "$type"; then
|
||||
INVALID_FRAGMENTS="$INVALID_FRAGMENTS\n - $filename (type: '$type')"
|
||||
fi
|
||||
done
|
||||
|
||||
if [ -n "$INVALID_FRAGMENTS" ]; then
|
||||
echo "❌ Error: Invalid changelog fragment types found:"
|
||||
echo -e "$INVALID_FRAGMENTS"
|
||||
echo ""
|
||||
echo "Valid types are: $VALID_TYPES"
|
||||
echo "Example: 1234.added.md, 5678.fixed.md"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "✓ Found $FRAGMENT_COUNT changelog fragment(s)"
|
||||
echo "has_fragments=true" >> $GITHUB_OUTPUT
|
||||
|
||||
- name: Preview changelog
|
||||
run: |
|
||||
echo "## Preview of changelog for version ${{ inputs.version }}"
|
||||
echo ""
|
||||
uv run towncrier build --draft --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}"
|
||||
|
||||
- name: Build changelog
|
||||
run: |
|
||||
uv run towncrier build --version "${{ inputs.version }}" --date "${{ steps.set_date.outputs.release_date }}" --yes
|
||||
|
||||
- name: Create Pull Request
|
||||
uses: peter-evans/create-pull-request@v7
|
||||
with:
|
||||
token: ${{ secrets.GITHUB_TOKEN }}
|
||||
commit-message: "Update changelog for version ${{ inputs.version }}"
|
||||
title: "Release ${{ inputs.version }} - Changelog Update"
|
||||
body: |
|
||||
## Changelog Update for Release ${{ inputs.version }}
|
||||
|
||||
This PR updates the CHANGELOG.md with all changes for version **${{ inputs.version }}**.
|
||||
|
||||
### Summary
|
||||
- **Version:** ${{ inputs.version }}
|
||||
- **Date:** ${{ steps.set_date.outputs.release_date }}
|
||||
- **Fragments processed:** ${{ steps.check_fragments.outputs.fragment_count }}
|
||||
|
||||
### What this PR does
|
||||
- ✅ Adds new release section to CHANGELOG.md
|
||||
- ✅ Removes processed changelog fragments
|
||||
- ✅ Ready to merge for release
|
||||
|
||||
### Next Steps
|
||||
1. Review the changelog entries below
|
||||
2. Make any necessary edits to CHANGELOG.md if needed
|
||||
3. Merge this PR
|
||||
4. Continue with your release process
|
||||
|
||||
---
|
||||
|
||||
<details>
|
||||
<summary>📋 Preview of changes</summary>
|
||||
|
||||
The changelog has been updated with entries from the following fragments:
|
||||
|
||||
```bash
|
||||
${{ steps.check_fragments.outputs.fragment_count }} fragments processed
|
||||
```
|
||||
|
||||
</details>
|
||||
branch: changelog-${{ inputs.version }}
|
||||
delete-branch: true
|
||||
labels: |
|
||||
changelog
|
||||
release
|
||||
1
.github/workflows/python-compatibility.yaml
vendored
1
.github/workflows/python-compatibility.yaml
vendored
@@ -50,6 +50,7 @@ jobs:
|
||||
run: |
|
||||
uv sync --group dev --all-extras \
|
||||
--no-extra krisp \
|
||||
--no-extra ultravox \
|
||||
--no-extra local-smart-turn \
|
||||
--no-extra moondream \
|
||||
--no-extra mlx-whisper
|
||||
|
||||
2
.github/workflows/tests.yaml
vendored
2
.github/workflows/tests.yaml
vendored
@@ -37,7 +37,7 @@ jobs:
|
||||
|
||||
- name: Install dependencies
|
||||
run: |
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain --extra websocket
|
||||
uv sync --group dev --extra anthropic --extra aws --extra google --extra langchain
|
||||
|
||||
- name: Test with pytest
|
||||
run: |
|
||||
|
||||
@@ -11,7 +11,7 @@ build:
|
||||
jobs:
|
||||
post_install:
|
||||
- pip install uv
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
- UV_PROJECT_ENVIRONMENT=$READTHEDOCS_VIRTUALENV_PATH uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
sphinx:
|
||||
configuration: docs/api/conf.py
|
||||
|
||||
396
CHANGELOG.md
396
CHANGELOG.md
@@ -5,387 +5,10 @@ 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).
|
||||
|
||||
<!-- towncrier release notes start -->
|
||||
|
||||
## [0.0.98] - 2025-12-17
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
|
||||
- Added `RimeNonJsonTTSService` which supports non-JSON streaming mode. This
|
||||
new class supports websocket streaming for the Arcana model.
|
||||
(PR [#3085](https://github.com/pipecat-ai/pipecat/pull/3085))
|
||||
|
||||
- Added additional functionality related to "thinking", for Google and
|
||||
Anthropic LLMs.
|
||||
|
||||
1. New typed parameters for Google and Anthropic LLMs that control the
|
||||
models' thinking behavior (like how much thinking to do, and whether to
|
||||
output thoughts or thought summaries):
|
||||
- `AnthropicLLMService.ThinkingConfig`
|
||||
- `GoogleLLMService.ThinkingConfig`
|
||||
2. New frames for representing thoughts output by LLMs:
|
||||
- `LLMThoughtStartFrame`
|
||||
- `LLMThoughtTextFrame`
|
||||
- `LLMThoughtEndFrame`
|
||||
3. A generic mechanism for recording LLM thoughts to context, used
|
||||
specifically to support Anthropic, whose thought signatures are expected
|
||||
to appear alongside the text of the thoughts within assistant context
|
||||
messages. See:
|
||||
- `LLMThoughtEndFrame.signature`
|
||||
- `LLMAssistantAggregator` handling of the above field
|
||||
- `AnthropicLLMAdapter` handling of `"thought"` context messages
|
||||
4. Google-specific logic for inserting thought signatures into the context,
|
||||
to help maintain thinking continuity in a chain of LLM calls. See:
|
||||
- `GoogleLLMService` sending `LLMMessagesAppendFrame`s to add
|
||||
LLM-specific
|
||||
`"thought_signature"` messages to context
|
||||
- `GeminiLLMAdapter` handling of `"thought_signature"` messages
|
||||
5. An expansion of `TranscriptProcessor` to process LLM thoughts in
|
||||
addition to user and assistant utterances. See:
|
||||
- `TranscriptProcessor(process_thoughts=True)` (defaults to `False`)
|
||||
- `ThoughtTranscriptionMessage`, which is now also emitted with the
|
||||
`"on_transcript_update"` event
|
||||
(PR [#3175](https://github.com/pipecat-ai/pipecat/pull/3175))
|
||||
|
||||
- Data and control frames can now be marked as non-interruptible by using the
|
||||
`UninterruptibleFrame` mixin. Frames marked as `UninterruptibleFrame` will
|
||||
not be interrupted during processing, and any queued frames of this type will
|
||||
be retained in the internal queues. This is useful when you need ordered
|
||||
frames (data or control) that should not be discarded or cancelled due to
|
||||
interruptions.
|
||||
(PR [#3189](https://github.com/pipecat-ai/pipecat/pull/3189))
|
||||
|
||||
- Added `on_conversation_detected` event to `VoicemaiDetector`.
|
||||
(PR [#3207](https://github.com/pipecat-ai/pipecat/pull/3207))
|
||||
|
||||
- Added `x-goog-api-client` header with Pipecat's version to all Google
|
||||
services' requests.
|
||||
(PR [#3208](https://github.com/pipecat-ai/pipecat/pull/3208))
|
||||
|
||||
- Added support for the HeyGen LiveAvatar API (see https://www.liveavatar.com/).
|
||||
(PR [#3210](https://github.com/pipecat-ai/pipecat/pull/3210))
|
||||
|
||||
- Added to `AWSNovaSonicLLMService` functionality related to the new (and now
|
||||
default) Nova 2 Sonic model (`"amazon.nova-2-sonic-v1:0"`):
|
||||
|
||||
- Added the `endpointing_sensitivity` parameter to control how quickly the
|
||||
model decides the user has stopped speaking.
|
||||
- Made the assistant-response-trigger hack a no-op. It's only needed for
|
||||
the older Nova Sonic model.
|
||||
(PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
|
||||
|
||||
- [Ultravox Realtime](https://docs.ultravox.ai) is now a supported
|
||||
speech-to-speech service.
|
||||
|
||||
- Added `UltravoxRealtimeLLMService` for the integration.
|
||||
- Added `49-ultravox-realtime.py` example (with tool calling).
|
||||
(PR [#3227](https://github.com/pipecat-ai/pipecat/pull/3227))
|
||||
|
||||
- Added Daily PSTN dial-in support to the development runner with `--dialin`
|
||||
flag. This includes:
|
||||
|
||||
- `/daily-dialin-webhook` endpoint that handles incoming Daily PSTN webhooks
|
||||
- Automatic Daily room creation with SIP configuration
|
||||
- `DialinSettings` and `DailyDialinRequest` types in `pipecat.runner.types`
|
||||
for type-safe dial-in data
|
||||
- The runner now mimics Pipecat Cloud's dial-in webhook handling for local
|
||||
development
|
||||
(PR [#3235](https://github.com/pipecat-ai/pipecat/pull/3235))
|
||||
|
||||
- Add Gladia session id to logs for `GladiaSTTService`.
|
||||
(PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
|
||||
|
||||
- Added `InworldHttpTTSService` which uses Inworld's HTTP based TTS service in
|
||||
either streaming or non-streaming mode. Note: This class was previously named
|
||||
`InworldTTSService`.
|
||||
(PR [#3239](https://github.com/pipecat-ai/pipecat/pull/3239))
|
||||
|
||||
- Added `language_hints_strict` parameter to `SonioxSTTService` to strictly
|
||||
enforces language hints. This ensures that transcription occurs in the
|
||||
specified language.
|
||||
(PR [#3245](https://github.com/pipecat-ai/pipecat/pull/3245))
|
||||
|
||||
- Added Pipecat library version info to the `about` field in the `bot-ready`
|
||||
RTVI message.
|
||||
(PR [#3248](https://github.com/pipecat-ai/pipecat/pull/3248))
|
||||
|
||||
- Added `VisionFullResponseStartFrame`, `VisionFullResponseEndFrame` and
|
||||
`VisionTextFrame`. This are used by vision services similar to LLM
|
||||
services.
|
||||
(PR [#3252](https://github.com/pipecat-ai/pipecat/pull/3252))
|
||||
|
||||
### Changed
|
||||
|
||||
- `FunctionCallInProgressFrame` and `FunctionCallResultFrame` have changed from
|
||||
system frames to a control frame and a data frame, respectively, and are
|
||||
now both marked as `UninterruptibleFrame`.
|
||||
(PR [#3189](https://github.com/pipecat-ai/pipecat/pull/3189))
|
||||
|
||||
- `UserBotLatencyLogObserver` now uses `VADUserStartedSpeakingFrame` and
|
||||
`VADUserStoppedSpeakingFrame` to determine latency from user stopped speaking
|
||||
to bot started speaking.
|
||||
(PR [#3206](https://github.com/pipecat-ai/pipecat/pull/3206))
|
||||
|
||||
- Updated `HeyGenVideoService` and `HeyGenTransport` to support both HeyGen
|
||||
APIs (Interactive Avatar and Live Avatar).
|
||||
Using them is as simple as specifying the `service_type` when creating the
|
||||
`HeyGenVideoService` and the `HeyGenTransport`:
|
||||
|
||||
```python
|
||||
heyGen = HeyGenVideoService(
|
||||
api_key=os.getenv("HEYGEN_LIVE_AVATAR_API_KEY"),
|
||||
service_type=ServiceType.LIVE_AVATAR,
|
||||
session=session,
|
||||
)
|
||||
```
|
||||
|
||||
(PR [#3210](https://github.com/pipecat-ai/pipecat/pull/3210))
|
||||
|
||||
- Made `"amazon.nova-2-sonic-v1:0"` the new default model for
|
||||
`AWSNovaSonicLLMService`.
|
||||
(PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
|
||||
|
||||
- Updated the `run_inference` methods in the LLM service classes
|
||||
(`AnthropicLLMService`, `AWSBedrockLLMService`, `GoogleLLMService`, and
|
||||
`OpenAILLMService` and its base classes) to use the provided LLM
|
||||
configuration parameters.
|
||||
(PR [#3214](https://github.com/pipecat-ai/pipecat/pull/3214))
|
||||
|
||||
- Updated default models for:
|
||||
|
||||
- `GeminiLiveLLMService` to `gemini-2.5-flash-native-audio-preview-12-2025`.
|
||||
- `GeminiLiveVertexLLMService` to `gemini-live-2.5-flash-native-audio`.
|
||||
(PR [#3228](https://github.com/pipecat-ai/pipecat/pull/3228))
|
||||
|
||||
- Changed the `reason` field in `EndFrame`, `CancelFrame`, `EndTaskFrame`, and
|
||||
`CancelTaskFrame` from `str` to `Any` to indicate that it can hold values
|
||||
other than strings.
|
||||
(PR [#3231](https://github.com/pipecat-ai/pipecat/pull/3231))
|
||||
|
||||
- Updated websocket STT services to use the `WebsocketSTTService` base class.
|
||||
This base class manages the websocket connection and handles reconnects.
|
||||
Updated services:
|
||||
|
||||
- `AssemblyAISTTService`
|
||||
- `AWSTranscribeSTTService`
|
||||
- `GladiaSTTService`
|
||||
- `SonioxSTTService`
|
||||
(PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
|
||||
|
||||
- Changed Inworld's TTS service implementations:
|
||||
|
||||
- Previously, the HTTP implementation was named `InworldTTSService`. That
|
||||
has been moved to `InworldHttpTTSService`. This service now supports
|
||||
word-timestamp alignment data in both streaming and non-streaming modes.
|
||||
- Updated the `InworldTTSService` class to use Inworld's Websocket API.
|
||||
This class now has support for word-timestamp alignment data and tracks
|
||||
contexts for each user turn.
|
||||
(PR [#3239](https://github.com/pipecat-ai/pipecat/pull/3239))
|
||||
|
||||
- ⚠️ Breaking change: `WordTTSService.start_word_timestamps()` and
|
||||
`WordTTSService.reset_word_timestamps()` are now async.
|
||||
(PR [#3240](https://github.com/pipecat-ai/pipecat/pull/3240))
|
||||
|
||||
- Updated the current RTVI version to 1.1.0 to reflect recent additions and
|
||||
deprecations.
|
||||
|
||||
- New RTVI Messages: `send-text` and `bot-output`
|
||||
- Deprecated Messages: `append-to-context` and `bot-transcription`
|
||||
(PR [#3248](https://github.com/pipecat-ai/pipecat/pull/3248))
|
||||
|
||||
- `MoondreamService` now pushes `VisionFullResponseStartFrame`,
|
||||
`VisionFullResponseEndFrame` and `VisionTextFrame`.
|
||||
(PR [#3252](https://github.com/pipecat-ai/pipecat/pull/3252))
|
||||
|
||||
### Deprecated
|
||||
|
||||
- `FalSmartTurnAnalyzer` and `LocalSmartTurnAnalyzer` are deprecated and will
|
||||
be removed in a future version. Use `LocalSmartTurnAnalyzerV3` instead.
|
||||
(PR [#3219](https://github.com/pipecat-ai/pipecat/pull/3219))
|
||||
|
||||
### Removed
|
||||
|
||||
- Removed the deprecated VLLM-based open source Ultravox STT service.
|
||||
(PR [#3227](https://github.com/pipecat-ai/pipecat/pull/3227))
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed a bug in `AWSNovaSonicLLMService` where we would mishandle cancelled
|
||||
tool calls in the context, resulting in errors.
|
||||
(PR [#3212](https://github.com/pipecat-ai/pipecat/pull/3212))
|
||||
|
||||
- Better support conversation history with Gemini 2.5 Flash Image (model
|
||||
"gemini-2.5-flash-image"). Prior to this fix, the model had no memory of
|
||||
previous images it had generated, so it wouldn't be able to iterate on
|
||||
them.
|
||||
(PR [#3224](https://github.com/pipecat-ai/pipecat/pull/3224))
|
||||
|
||||
- Support conversations with Gemini 3 Pro Image (model
|
||||
"gemini-3-pro-image-preview"). Prior to this fix, after the model generated
|
||||
an image the conversation would not be able to progress.
|
||||
(PR [#3224](https://github.com/pipecat-ai/pipecat/pull/3224))
|
||||
|
||||
- Fixed an issue where `ElevenLabsHttpTTSService` was not updating
|
||||
voice settings when receiving a `TTSUpdateSettingsFrame`.
|
||||
(PR [#3226](https://github.com/pipecat-ai/pipecat/pull/3226))
|
||||
|
||||
- Fixed the return type for `SmallWebRTCRequestHandler.handle_web_request()`
|
||||
function.
|
||||
(PR [#3230](https://github.com/pipecat-ai/pipecat/pull/3230))
|
||||
|
||||
- Fix a bug in LLM context audio content handling
|
||||
(PR [#3234](https://github.com/pipecat-ai/pipecat/pull/3234))
|
||||
|
||||
- In `GladiaSTTService`, reset the `_bytes_sent` counter on connecting the
|
||||
websocket. This avoids unnecessary audio buffer trimming.
|
||||
(PR [#3236](https://github.com/pipecat-ai/pipecat/pull/3236))
|
||||
|
||||
- Fixed a TTS service word-timestamp issue that could cause generated
|
||||
`TTSTextFrame` instances to have an incorrect pts (`pts = -1`).
|
||||
(PR [#3240](https://github.com/pipecat-ai/pipecat/pull/3240))
|
||||
|
||||
- Fixed an issue in `SimpleTextAggreagtor` where spaces were not being stripped
|
||||
before returning the aggregation. This resulted in an extra space for TTS
|
||||
services that don't support word-timestamp alignment data.
|
||||
(PR [#3247](https://github.com/pipecat-ai/pipecat/pull/3247))
|
||||
|
||||
## [0.0.97] - 2025-12-05
|
||||
|
||||
### Added
|
||||
|
||||
- Added new Gradium services, `GradiumSTTService` and `GradiumTTSService`, for
|
||||
speech-to-text and text-to-speech functionality using Gradium's API.
|
||||
|
||||
- Additions for `AsyncAITTSService` and `AsyncAIHttpTTSService`:
|
||||
|
||||
- Added new `languages`: `pt`, `nl`, `ar`, `ru`, `ro`, `ja`, `he`, `hy`,
|
||||
`tr`, `hi`, `zh`.
|
||||
- Updated the default model to `asyncflow_multilingual_v1.0` for improved
|
||||
accuracy and broader language coverage.
|
||||
|
||||
- Added optional tool and tool output filters for MCP services.
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated Deepgram logging to include Deepgram request IDs for improved
|
||||
debugging.
|
||||
|
||||
- Text Aggregation Improvements:
|
||||
|
||||
- **Breaking Change**: `BaseTextAggregator.aggregate()` now returns
|
||||
`AsyncIterator[Aggregation]` instead of `Optional[Aggregation]`. This
|
||||
enables the aggregator to return multiple results based on the provided
|
||||
text.
|
||||
- Refactored text aggregators to use inheritance: `SkipTagsAggregator` and
|
||||
`PatternPairAggregator` now inherit from `SimpleTextAggregator`, reusing
|
||||
the base class's sentence detection logic.
|
||||
|
||||
- Improved interruption handling to prevent bots from repeating themselves. LLM
|
||||
services that return multiple sentences in a single response (e.g.,
|
||||
`GoogleLLMService`) are now split into individual sentences before being sent
|
||||
to TTS. This ensures interruptions occur at sentence boundaries, preventing
|
||||
the bot from repeating content after being interrupted during long responses.
|
||||
|
||||
- Updated `AICFilter` to use Quail STT as the default model
|
||||
(`AICModelType.QUAIL_STT`). Quail STT is optimized for human-to-machine
|
||||
interaction (e.g., voice agents, speech-to-text) and operates at a native
|
||||
sample rate of 16 kHz with fixed enhancement parameters.
|
||||
|
||||
- If an unexpected exception is caught, or if `FrameProcessor.push_error()` is
|
||||
called with an exception, the file name and line number where the exception
|
||||
occured are now logged.
|
||||
|
||||
- Updated Smart Turn model weights to v3.1.
|
||||
|
||||
- Smart Turn analyzer now uses the full context of the turn rather than just
|
||||
the audio since VAD last triggered.
|
||||
|
||||
- Updated `CartesiaSTTService` to return the full transcription `result` in the
|
||||
`TranscriptionFrame` and `InterimTranscriptionFrame`. This provides access to
|
||||
word timestamp data.
|
||||
|
||||
- `HumeTTSService` changes:
|
||||
|
||||
- Added tracking headers (`X-Hume-Client-Name` and `X-Hume-Client-Version`)
|
||||
to all requests made by `HumeTTSService` to the Hume API for better usage
|
||||
tracking and analytics.
|
||||
- Added `stop()` and `cancel()` cleanup methods to `HumeTTSService` to
|
||||
properly close the HTTP client and prevent resource leaks.
|
||||
|
||||
### Deprecated
|
||||
|
||||
- NVIDIA Services name changes (all functionality is unchanged):
|
||||
|
||||
- `NimLLMService` is now deprecated, use `NvidiaLLMService` instead.
|
||||
- `RivaSTTService` is now deprecated, use `NvidiaSTTService` instead.
|
||||
- `RivaTTSService` is now deprecated, use `NvidiaTTSService` instead.
|
||||
- Use `uv pip install pipecat-ai[nvidia]` instead of
|
||||
`uv pip install pipecat-ai[riva]`
|
||||
|
||||
- The `noise_gate_enable` parameter in `AICFilter` is deprecated and no longer
|
||||
has any effect. Noise gating is now handled automatically by the AIC VAD
|
||||
system. Use `AICFilter.create_vad_analyzer()` for VAD functionality instead.
|
||||
|
||||
- Package `pipecat.sync` is deprecated, use `pipecat.utils.sync` instead.
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed bug in `PatternPairAggregator` where pattern handlers could be called
|
||||
multiple times for `KEEP` or `AGGREGATE` patterns.
|
||||
|
||||
- Fixed sentence aggregation to correctly handle ambiguous punctuation in
|
||||
streaming text, such as currency ("$29.95") and abbreviations ("Mr. Smith").
|
||||
|
||||
- Fixed an issue in `AWSTranscribeSTTService` where the `region` arg was always
|
||||
set to `us-east-1` when providing an AWS_REGION env var.
|
||||
|
||||
- Fixed an issue in `SarvamTTSService` where the last sentence was not being
|
||||
spoken. Now, audio is flushed when the TTS services receives the
|
||||
`LLMFullResponseEndFrame` or `EndFrame`.
|
||||
|
||||
- Fixed an issue in `DeepgramTTSService` where a `TTSStoppedFrame` was
|
||||
incorrectly pushed after a functional call. This caused an issue with the
|
||||
voice-ui-kit's conversational panel rending of the LLM output after a
|
||||
function call.
|
||||
|
||||
- Fixed an issue where `LLMTextFrame.skip_tts` was being overwritten by LLM
|
||||
services.
|
||||
|
||||
- Fixed an issue that caused `WebsocketService` instances to attempt
|
||||
reconnection during shutdown.
|
||||
|
||||
- Fixed an issue in `ElevenLabsTTSService` where character usage metrics were
|
||||
only reported on the first TTS generation per turn.
|
||||
|
||||
## [0.0.96] - 2025-11-26 🦃 "Happy Thanksgiving!" 🦃
|
||||
|
||||
### Added
|
||||
|
||||
- Added `AWSBedrockAgentCoreProcessor` to support invoking an AgentCore-hosted
|
||||
agent in a Pipecat pipeline.
|
||||
|
||||
- Enhanced error handling across the framework:
|
||||
|
||||
- Added `on_error` callback to `FrameProcessor` for centralized error
|
||||
handling.
|
||||
|
||||
- Renamed `push_error(error: ErrorFrame)` to `push_error_frame(error: ErrorFrame)`
|
||||
for clarity.
|
||||
|
||||
- Added new `push_error` method for simplified error reporting:
|
||||
|
||||
```python
|
||||
async def push_error(error_msg: str,
|
||||
exception: Optional[Exception] = None,
|
||||
fatal: bool = False)
|
||||
```
|
||||
|
||||
- Standardized error logging by replacing `logger.exception` calls with
|
||||
`logger.error` throughout the codebase.
|
||||
|
||||
- Added `cache_read_input_tokens`, `cache_creation_input_tokens` and
|
||||
`reasoning_tokens` to OTel spans for LLM call
|
||||
|
||||
- Added `LiveKitRESTHelper` utility class for managing LiveKit rooms via REST API.
|
||||
|
||||
- Added `DeepgramSageMakerSTTService` which connects to a SageMaker hosted
|
||||
@@ -465,18 +88,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
- Added new emotions: calm and fluent
|
||||
|
||||
- Added `enable_logging` to `SimliVideoService` input parameters. It's disabled
|
||||
by default.
|
||||
|
||||
### Changed
|
||||
|
||||
- Updated `FishAudioTTSService` default model to `s1`.
|
||||
|
||||
- Updated `DeepgramTTSService` to use Deepgram's TTS websocket API. ⚠️ This is
|
||||
a potential breaking change, which only affects you if you're self-hosting
|
||||
`DeepgramTTSService`. The new service uses Websockets and improves TTFB
|
||||
latency.
|
||||
|
||||
- Updated `daily-python` to 0.22.0.
|
||||
|
||||
- `BaseTextAggregator` changes:
|
||||
@@ -634,11 +247,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
### Fixed
|
||||
|
||||
- Fixed an issue in `AWSBedrockLLMService` where the `aws_region` arg was
|
||||
always set to `us-east-1` when providing an AWS_REGION env var.
|
||||
|
||||
- Fixed an issue with `DeepgramFluxSTTService` where it sometimes failed to reconnect.
|
||||
|
||||
- Fixed an issue in `ElevenLabsRealtimeSTTService` where dynamic language
|
||||
updates were not working.
|
||||
|
||||
@@ -2199,7 +1807,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
compatibility issues with other packages. Now you can use the PlayHT HTTP
|
||||
service with other services, like GoogleLLMService.
|
||||
|
||||
- Updated `pyproject.toml` to once again pin `numba` to `==0.61.2` in order to
|
||||
- Updated `pyproject.toml` to once again pin `numba` to `>=0.61.2` in order to
|
||||
resolve package versioning issues.
|
||||
|
||||
- Updated the `STTMuteFilter` to include `VADUserStartedSpeakingFrame` and
|
||||
|
||||
@@ -79,7 +79,7 @@ Once your PR is submitted, post in the `#community-integrations` Discord channel
|
||||
|
||||
**Examples:**
|
||||
|
||||
- [NvidiaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/nvidia/stt.py)
|
||||
- [RivaSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/riva/stt.py)
|
||||
- [FalSTTService](https://github.com/pipecat-ai/pipecat/blob/main/src/pipecat/services/fal/stt.py)
|
||||
|
||||
#### Key requirements:
|
||||
|
||||
106
CONTRIBUTING.md
106
CONTRIBUTING.md
@@ -17,122 +17,24 @@ We welcome contributions of all kinds! Your help is appreciated. Follow these st
|
||||
git checkout -b your-branch-name
|
||||
```
|
||||
4. **Make your changes**: Edit or add files as necessary.
|
||||
5. **Add a changelog entry**: Create a changelog fragment file (see [Changelog Entries](#changelog-entries) below).
|
||||
6. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
7. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
5. **Test your changes**: Ensure that your changes look correct and follow the style set in the codebase.
|
||||
6. **Commit your changes**: Once you're satisfied with your changes, commit them with a meaningful message.
|
||||
|
||||
```bash
|
||||
git commit -m "Description of your changes"
|
||||
```
|
||||
|
||||
8. **Push your changes**: Push your branch to your forked repository.
|
||||
7. **Push your changes**: Push your branch to your forked repository.
|
||||
|
||||
```bash
|
||||
git push origin your-branch-name
|
||||
```
|
||||
|
||||
9. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
8. **Submit a Pull Request (PR)**: Open a PR from your forked repository to the main branch of this repo.
|
||||
> Important: Describe the changes you've made clearly!
|
||||
|
||||
Our maintainers will review your PR, and once everything is good, your contributions will be merged!
|
||||
|
||||
## Changelog Entries
|
||||
|
||||
Every pull request that makes a user-facing change should include a changelog entry. We use a changelog fragment system to avoid merge conflicts.
|
||||
|
||||
### Creating a Changelog Fragment
|
||||
|
||||
1. Create a new file in the `changelog/` directory with this naming pattern:
|
||||
|
||||
```
|
||||
<PR_number>.<type>.md
|
||||
```
|
||||
|
||||
2. Choose the appropriate type:
|
||||
|
||||
- `added.md` - New features
|
||||
- `changed.md` - Changes in existing functionality
|
||||
- `deprecated.md` - Soon-to-be removed features
|
||||
- `removed.md` - Removed features
|
||||
- `fixed.md` - Bug fixes
|
||||
- `security.md` - Security fixes
|
||||
- `other.md` - Other changes (documentation, dependencies, etc.)
|
||||
|
||||
3. Write your changelog entry as a Markdown bullet point. Include the `-` at the start:
|
||||
|
||||
**Example files:**
|
||||
|
||||
`changelog/1234.added.md`:
|
||||
|
||||
```markdown
|
||||
- Added support for Anthropic Claude 3.5 Sonnet with improved streaming performance.
|
||||
```
|
||||
|
||||
`changelog/5678.fixed.md`:
|
||||
|
||||
```markdown
|
||||
- Fixed an issue where audio frames were dropped during high-load scenarios.
|
||||
```
|
||||
|
||||
**For entries with nested bullets:**
|
||||
|
||||
`changelog/1234.changed.md`:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
### Multiple Changes in One PR
|
||||
|
||||
**Different types of changes:** Create separate fragment files for each type:
|
||||
|
||||
```
|
||||
changelog/1234.added.md
|
||||
changelog/1234.fixed.md
|
||||
```
|
||||
|
||||
**Multiple changes of the same type:** Create numbered fragment files:
|
||||
|
||||
```
|
||||
changelog/1234.changed.md
|
||||
changelog/1234.changed.2.md
|
||||
```
|
||||
|
||||
**Related changes:** Use nested bullets in a single fragment:
|
||||
|
||||
```markdown
|
||||
- Updated service configuration:
|
||||
|
||||
- Changed default timeout to 30 seconds
|
||||
- Added retry logic for failed connections
|
||||
```
|
||||
|
||||
**Rule of thumb:** One logical change per fragment file. If changes are unrelated, use separate files.
|
||||
|
||||
### Preview Your Changes
|
||||
|
||||
To see what your changelog entry will look like:
|
||||
|
||||
```bash
|
||||
towncrier build --draft --version Unreleased
|
||||
```
|
||||
|
||||
This won't modify any files, just show you a preview.
|
||||
|
||||
### When to Skip Changelog Entries
|
||||
|
||||
You can skip adding a changelog entry for:
|
||||
|
||||
- Documentation-only changes
|
||||
- Internal refactoring with no user-facing impact
|
||||
- Test-only changes
|
||||
- CI/build configuration changes
|
||||
|
||||
If you're unsure whether your change needs a changelog entry, ask in your PR!
|
||||
|
||||
## Dependency Management
|
||||
|
||||
This project uses [uv](https://docs.astral.sh/uv/) for dependency management. The `uv.lock` file is committed to ensure reproducible builds.
|
||||
|
||||
2
LICENSE
2
LICENSE
@@ -1,6 +1,6 @@
|
||||
BSD 2-Clause License
|
||||
|
||||
Copyright (c) 2024–2026, Daily
|
||||
Copyright (c) 2024–2025, Daily
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are met:
|
||||
|
||||
28
README.md
28
README.md
@@ -3,6 +3,7 @@
|
||||
</div></h1>
|
||||
|
||||
[](https://pypi.org/project/pipecat-ai)  [](https://codecov.io/gh/pipecat-ai/pipecat) [](https://docs.pipecat.ai) [](https://discord.gg/pipecat) [](https://deepwiki.com/pipecat-ai/pipecat)
|
||||
[](https://getmanta.ai/pipecat)
|
||||
|
||||
# 🎙️ Pipecat: Real-Time Voice & Multimodal AI Agents
|
||||
|
||||
@@ -71,19 +72,19 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
| Category | Services |
|
||||
| ------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Gradium](https://docs.pipecat.ai/server/services/stt/gradium), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Gradium](https://docs.pipecat.ai/server/services/tts/gradium), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [Grok Voice Agent](https://docs.pipecat.ai/server/services/s2s/grok), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai), [Ultravox](https://docs.pipecat.ai/server/services/s2s/ultravox), |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) |
|
||||
| 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), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-filter) |
|
||||
| Analytics & Metrics | [OpenTelemetry](https://docs.pipecat.ai/server/utilities/opentelemetry), [Sentry](https://docs.pipecat.ai/server/services/analytics/sentry) |
|
||||
| Category | Services |
|
||||
| ------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Speech-to-Text | [AssemblyAI](https://docs.pipecat.ai/server/services/stt/assemblyai), [AWS](https://docs.pipecat.ai/server/services/stt/aws), [Azure](https://docs.pipecat.ai/server/services/stt/azure), [Cartesia](https://docs.pipecat.ai/server/services/stt/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/stt/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/stt/elevenlabs), [Fal Wizper](https://docs.pipecat.ai/server/services/stt/fal), [Gladia](https://docs.pipecat.ai/server/services/stt/gladia), [Google](https://docs.pipecat.ai/server/services/stt/google), [Groq (Whisper)](https://docs.pipecat.ai/server/services/stt/groq), [NVIDIA Riva](https://docs.pipecat.ai/server/services/stt/riva), [OpenAI (Whisper)](https://docs.pipecat.ai/server/services/stt/openai), [SambaNova (Whisper)](https://docs.pipecat.ai/server/services/stt/sambanova), [Sarvam](https://docs.pipecat.ai/server/services/stt/sarvam), [Soniox](https://docs.pipecat.ai/server/services/stt/soniox), [Speechmatics](https://docs.pipecat.ai/server/services/stt/speechmatics), [Ultravox](https://docs.pipecat.ai/server/services/stt/ultravox), [Whisper](https://docs.pipecat.ai/server/services/stt/whisper) |
|
||||
| LLMs | [Anthropic](https://docs.pipecat.ai/server/services/llm/anthropic), [AWS](https://docs.pipecat.ai/server/services/llm/aws), [Azure](https://docs.pipecat.ai/server/services/llm/azure), [Cerebras](https://docs.pipecat.ai/server/services/llm/cerebras), [DeepSeek](https://docs.pipecat.ai/server/services/llm/deepseek), [Fireworks AI](https://docs.pipecat.ai/server/services/llm/fireworks), [Gemini](https://docs.pipecat.ai/server/services/llm/gemini), [Grok](https://docs.pipecat.ai/server/services/llm/grok), [Groq](https://docs.pipecat.ai/server/services/llm/groq), [Mistral](https://docs.pipecat.ai/server/services/llm/mistral), [NVIDIA NIM](https://docs.pipecat.ai/server/services/llm/nim), [Ollama](https://docs.pipecat.ai/server/services/llm/ollama), [OpenAI](https://docs.pipecat.ai/server/services/llm/openai), [OpenRouter](https://docs.pipecat.ai/server/services/llm/openrouter), [Perplexity](https://docs.pipecat.ai/server/services/llm/perplexity), [Qwen](https://docs.pipecat.ai/server/services/llm/qwen), [SambaNova](https://docs.pipecat.ai/server/services/llm/sambanova) [Together AI](https://docs.pipecat.ai/server/services/llm/together) |
|
||||
| Text-to-Speech | [Async](https://docs.pipecat.ai/server/services/tts/asyncai), [AWS](https://docs.pipecat.ai/server/services/tts/aws), [Azure](https://docs.pipecat.ai/server/services/tts/azure), [Cartesia](https://docs.pipecat.ai/server/services/tts/cartesia), [Deepgram](https://docs.pipecat.ai/server/services/tts/deepgram), [ElevenLabs](https://docs.pipecat.ai/server/services/tts/elevenlabs), [Fish](https://docs.pipecat.ai/server/services/tts/fish), [Google](https://docs.pipecat.ai/server/services/tts/google), [Groq](https://docs.pipecat.ai/server/services/tts/groq), [Hume](https://docs.pipecat.ai/server/services/tts/hume), [Inworld](https://docs.pipecat.ai/server/services/tts/inworld), [LMNT](https://docs.pipecat.ai/server/services/tts/lmnt), [MiniMax](https://docs.pipecat.ai/server/services/tts/minimax), [Neuphonic](https://docs.pipecat.ai/server/services/tts/neuphonic), [NVIDIA Riva](https://docs.pipecat.ai/server/services/tts/riva), [OpenAI](https://docs.pipecat.ai/server/services/tts/openai), [Piper](https://docs.pipecat.ai/server/services/tts/piper), [PlayHT](https://docs.pipecat.ai/server/services/tts/playht), [Rime](https://docs.pipecat.ai/server/services/tts/rime), [Sarvam](https://docs.pipecat.ai/server/services/tts/sarvam), [Speechmatics](https://docs.pipecat.ai/server/services/tts/speechmatics), [XTTS](https://docs.pipecat.ai/server/services/tts/xtts) |
|
||||
| Speech-to-Speech | [AWS Nova Sonic](https://docs.pipecat.ai/server/services/s2s/aws), [Gemini Multimodal Live](https://docs.pipecat.ai/server/services/s2s/gemini), [OpenAI Realtime](https://docs.pipecat.ai/server/services/s2s/openai) |
|
||||
| Transport | [Daily (WebRTC)](https://docs.pipecat.ai/server/services/transport/daily), [FastAPI Websocket](https://docs.pipecat.ai/server/services/transport/fastapi-websocket), [SmallWebRTCTransport](https://docs.pipecat.ai/server/services/transport/small-webrtc), [WebSocket Server](https://docs.pipecat.ai/server/services/transport/websocket-server), Local |
|
||||
| Serializers | [Plivo](https://docs.pipecat.ai/server/utilities/serializers/plivo), [Twilio](https://docs.pipecat.ai/server/utilities/serializers/twilio), [Telnyx](https://docs.pipecat.ai/server/utilities/serializers/telnyx) |
|
||||
| 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), [ai-coustics](https://docs.pipecat.ai/server/utilities/audio/aic-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)
|
||||
|
||||
@@ -153,6 +154,7 @@ You can get started with Pipecat running on your local machine, then move your a
|
||||
--no-extra gstreamer \
|
||||
--no-extra krisp \
|
||||
--no-extra local \
|
||||
--no-extra ultravox # (ultravox not fully supported on macOS)
|
||||
```
|
||||
|
||||
3. Install the git pre-commit hooks:
|
||||
|
||||
@@ -1,42 +0,0 @@
|
||||
- Introducing user turn strategies. User turn strategies indicate when the user turn starts or stops. In conversational agents, these are often referred to as start/stop speaking or turn-taking plans or policies.
|
||||
|
||||
User turn start strategies indicate when the user starts speaking (e.g. using VAD events or when a user says one or more words).
|
||||
|
||||
User turn stop strategies indicate when the user stops speaking (e.g. using an end-of-turn detection model or by observing incoming transcriptions).
|
||||
|
||||
A list of strategies can be specified for both strategies; strategies are evaluated in order until one evaluates to true.
|
||||
|
||||
Available user turn start strategies:
|
||||
- VADUserTurnStartStrategy
|
||||
- TranscriptionUserTurnStartStrategy
|
||||
- MinWordsUserTurnStartStrategy
|
||||
- ExternalUserTurnStartStrategy
|
||||
|
||||
Available user turn stop strategies:
|
||||
- TranscriptionUserTurnStopStrategy
|
||||
- TurnAnalyzerUserTurnStopStrategy
|
||||
- ExternalUserTurnStopStrategy
|
||||
|
||||
The default strategies are:
|
||||
|
||||
- start: [VADUserTurnStartStrategy, TranscriptionUserTurnStartStrategy]
|
||||
- stop: [TranscriptionUserTurnStopStrategy]
|
||||
|
||||
Turn strategies are configured when setting up `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams())
|
||||
)
|
||||
],
|
||||
)
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use the user turn strategies you must update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- ⚠️ `TransportParams.turn_analyzer` is deprecated and might result in unexpected behavior, use `LLMUserAggregator`'s new `user_turn_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruption_strategies` is deprecated, use `LLMUserAggregator`'s new `user_turn_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `EmulateUserStartedSpeakingFrame` and `EmulateUserStoppedSpeakingFrame` frames are deprecated.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated the `emulated` field in the `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames.
|
||||
@@ -1 +0,0 @@
|
||||
- The `LLMUserAggregatorParams` and `LLMAssistantAggregatorParams` classes in `pipecat.processors.aggregators.llm_response` are now deprecated. Use the new universal `LLMContext` and `LLMContextAggregatorPair` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- `pipecat.audio.interruptions.MinWordsInterruptionStrategy` is deprecated. Use `pipecat.turns.user_start.MinWordsUserTurnStartStrategy` with `LLMUserAggregator`'s new `user_turn_strategies` parameter instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `RNNoiseFilter` for real-time noise suppression using RNNoise neural network via pyrnnoise library.
|
||||
@@ -1,7 +0,0 @@
|
||||
- Updated `ElevenLabsRealtimeSTTService` to accept the `include_language_detection` parameter to detect language.
|
||||
```python
|
||||
stt = ElevenLabsRealtimeSTTService(
|
||||
api_key=os.getenv("ELEVENLABS_API_KEY"),
|
||||
include_language_detection=True
|
||||
)
|
||||
```
|
||||
@@ -1,15 +0,0 @@
|
||||
- Updated `SpeechmaticsSTTService` to use new Python Voice SDK with improved VAD,
|
||||
Smart Turn capabilities, and brings dramatic improvements to latency without
|
||||
any impact on accuracy. Use the `turn_detection_mode` parameter to control the
|
||||
endpointing of speech, with `TurnDetectionMode.EXTERNAL` (default),
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`.
|
||||
```python
|
||||
stt = SpeechmaticsSTTService(
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1,4 +0,0 @@
|
||||
- For `SpeechmaticsSTTService`, the `end_of_utterance_mode` parameter is deprecated.
|
||||
Use the new `turn_detection_mode` parameter instead, with `TurnDetectionMode.EXTERNAL`,
|
||||
`TurnDetectionMode.ADAPTIVE`, or `TurnDetectionMode.SMART_TURN`. The `enable_vad`
|
||||
parameter is also deprecated and is inferred from the `turn_detection_mode`.
|
||||
@@ -1,2 +0,0 @@
|
||||
- Improved error handling in `ElevenLabsRealtimeSTTService`
|
||||
- Fixed an issue in `ElevenLabsRealtimeSTTService` causing an infinite loop that blocks the process if the websocket disconnects due to an error
|
||||
@@ -1 +0,0 @@
|
||||
- `TranscriptionFrame` and `InterimTranscriptionFrame` produced by `DailyTransport` now include the transport source (i.e., the originating audio track).
|
||||
@@ -1 +0,0 @@
|
||||
- `daily-python` updated to 0.23.0.
|
||||
@@ -1,15 +0,0 @@
|
||||
- `OpenAILLMContext` and its associated things (context aggregators, etc.) are now deprecated in favor of the universal `LLMContext` and its associated things.
|
||||
|
||||
From the developer's point of view, switching to using `LLMContext` machinery will usually be a matter of going from this:
|
||||
|
||||
```python
|
||||
context = OpenAILLMContext(messages, tools)
|
||||
context_aggregator = llm.create_context_aggregator(context)
|
||||
```
|
||||
|
||||
To this:
|
||||
|
||||
```
|
||||
context = LLMContext(messages, tools)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
```
|
||||
@@ -1,8 +0,0 @@
|
||||
- Added `GrokRealtimeLLMService` for xAI's Grok Voice Agent API with real-time voice conversations:
|
||||
|
||||
- Support for real-time audio streaming with WebSocket connection
|
||||
- Built-in server-side VAD (Voice Activity Detection)
|
||||
- Multiple voice options: Ara, Rex, Sal, Eve, Leo
|
||||
- Built-in tools support: web_search, x_search, file_search
|
||||
- Custom function calling with standard Pipecat tools schema
|
||||
- Configurable audio formats (PCM at 8kHz-48kHz)
|
||||
@@ -1 +0,0 @@
|
||||
- Added an approximation of TTFB for Ultravox.
|
||||
@@ -1,5 +0,0 @@
|
||||
- Updates to Inworld TTS services:
|
||||
|
||||
- Improved `InworldTTSService`'s websocket implementation to better flush and
|
||||
close context to better handle long inputs.
|
||||
- Improved docstrings for `InworldTTSService` and `InworldHttpTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a new `AudioContextTTSService` to the TTS service base classes. The `AudioContextWordTTSService` now inherits from `AudioContextTTSService` and `WebsocketWordTTSService`.
|
||||
@@ -1,4 +0,0 @@
|
||||
- `LLMUserAggregator` now exposes the following events:
|
||||
- `on_user_turn_started`: triggered when a user turn starts
|
||||
- `on_user_turn_stopped`: triggered when a user turn ends
|
||||
- `on_user_turn_stop_timeout`: triggered when a user turn does not stop and times out
|
||||
@@ -1,29 +0,0 @@
|
||||
- Introducing user mute strategies. User mute strategies indicate when user input should be muted based on the current system state.
|
||||
|
||||
In conversational agents, user mute strategies are used to prevent user input from interrupting bot speech, tool execution, or other critical system operations.
|
||||
|
||||
A list of strategies can be specified; all strategies are evaluated for every frame so that each strategy can maintain its internal state. A user frame is muted if any of the configured strategies indicates it should be muted.
|
||||
|
||||
Available user mute strategies:
|
||||
|
||||
* `FirstSpeechUserMuteStrategy`
|
||||
* `MuteUntilFirstBotCompleteUserMuteStrategy`
|
||||
* `AlwaysUserMuteStrategy`
|
||||
* `FunctionCallUserMuteStrategy`
|
||||
|
||||
User mute strategies replace the legacy `STTMuteFilter` and provide a more flexible and composable approach to muting user input.
|
||||
|
||||
User mute strategies are configured when setting up the `LLMContextAggregatorPair`. For example:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_mute_strategies=[
|
||||
FirstSpeechUserMuteStrategy(),
|
||||
]
|
||||
),
|
||||
)
|
||||
```
|
||||
|
||||
In order to use user mute strategies you should update to the new universal `LLMContext` and `LLMContextAggregatorPair`.
|
||||
@@ -1 +0,0 @@
|
||||
- `STTMuteFilter` is deprecated and will be removed in a future version. Use `LLMUserAggregator`'s new `user_mute_strategies` instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a bug in `STTMuteFilter` where the user was not always muted during function calls, especially when there were multiple simultaneous calls.
|
||||
@@ -1 +0,0 @@
|
||||
- `FrameProcessor.interruptions_allowed` is now deprecated, use `LLMUserAggregator`'s new parameter `user_mute_strategies` instead.
|
||||
@@ -1,12 +0,0 @@
|
||||
- `PipelineParams.allow_interruptions` is now deprecated, use `LLMUserAggregator`'s new parameter `user_turn_strategies` instead. For example, to disable interruptions but still get user turns you can do:
|
||||
|
||||
```python
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
start=[TranscriptionUserTurnStartStrategy(enable_interruptions=False)],
|
||||
),
|
||||
),
|
||||
)
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- Added `use_ssl` parameter to `NvidiaSTTService`, `NvidiaSegmentedSTTService` and `NvidiaTTSService`.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `DeepgramSTTService` to push user started/stopped speaking and interruption frames when `vad_enabled` is set to true. This centralizes the frames into the service, removing the need to have your application code handle Deepgram's events and push these frames.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `enable_interruptions` constructor argument to all user turn strategies. This tells the `LLMUserAggregator` to push or not push an `InterruptionFrame`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `52-live-transcription.py` foundational example demonstrating live transcription and translation from English to Spanish. In this example, the bot is not interruptible: as the user continues speaking, English transcriptions are queued, and the bot continuously translates and speaks each queued sentence in Spanish without being interrupted by new user speech.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed a `RNNoiseFilter` issue that would cause a "[Errno 12] Cannot allocate memory" error when processing silence audio frames.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `split_sentences` parameter to `SpeechmaticsSTTService` to control sentence splitting behavior for finals on sentence boundaries.
|
||||
@@ -1,4 +0,0 @@
|
||||
- Updated `SpeechmaticsSTTService` for version `0.0.99+`:
|
||||
- Fixed `SpeechmaticsSTTService` to listen for `VADUserStoppedSpeakingFrame` in order to finalize transcription.
|
||||
- Default to `TurnDetectionMode.FIXED` for Pipecat-controlled end of turn detection.
|
||||
- Only emit VAD + interruption frames if VAD is enabled within the plugin (modes other than `TurnDetectionMode.FIXED` or `TurnDetectionMode.EXTERNAL`).
|
||||
@@ -1 +0,0 @@
|
||||
- Added encoding validation to `DeepgramTTSService` to prevent unsupported encodings from reaching the API. The service now raises `ValueError` at initialization with a clear error message.
|
||||
@@ -1,2 +0,0 @@
|
||||
- Added word-level timestamp support to `AzureTTSService` for accurate text-to-audio synchronization.
|
||||
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `read_audio_frame` & `read_video_frame` methods in `SmallWebRTCClient` to check if the track is enabled before logging a warning.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed an issue with function calling where a handler failing to invoke its result callback could leave the context stuck in IN_PROGRESS, causing LLM inference for subsequent function call results to block while waiting on the unresolved call.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed an issue with DeepgramTTSService where the model would output "Dot" instead of a period in some circumstances.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `pronunciation_dict_id` parameter to `CartesiaTTSService.InputParams` and `CartesiaHttpTTSService.InputParams` to support Cartesia's pronunciation dictionary feature for custom pronunciations.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed an issue in GeminiLiveLLMService where TranscriptionFrames were occasionally not pushed.
|
||||
@@ -1 +0,0 @@
|
||||
- Added support for using the HeyGen LiveAvatar API with the `HeyGenTransport` (see https://www.liveavatar.com/).
|
||||
@@ -1,8 +0,0 @@
|
||||
- Added image support to `OpenAIRealtimeLLMService` via `InputImageRawFrame`:
|
||||
- New `start_video_paused` parameter to control initial video input state
|
||||
- New `video_frame_detail` parameter to set image processing quality ("auto",
|
||||
"low", or "high"). This corresponds to OpenAI Realtime's `image_detail`
|
||||
parameter.
|
||||
- `set_video_input_paused()` method to pause/resume video input at runtime
|
||||
- `set_video_frame_detail()` method to adjust video frame quality dynamically
|
||||
- Automatic rate limiting (1 frame per second) to prevent API overload
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `CartesiaTTSService` to support setting `language=None`, resulting in Cartesia auto-detecting the language of the conversation.
|
||||
@@ -1,3 +0,0 @@
|
||||
- The bundled Smart Turn weights are now updated to v3.2, which has better
|
||||
handling of short utterances, and is more robust against background
|
||||
noise.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated `SpeechmaticsSTTService` dependency to `speechmatics-voice[smart]>=0.2.6`
|
||||
@@ -1 +0,0 @@
|
||||
- Added `UserTurnProcessor`, a frame processor built on `UserTurnController` that pushes `UserStartedSpeakingFrame` and `UserStoppedSpeakingFrame` frames and interruptions based on the controller's user turn strategies.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `UserTurnController` to manage user turns. It emits `on_user_turn_started`, `on_user_turn_stopped`, and `on_user_turn_stop_timeout` events, and can be integrated into processors to detect and handle user turns. `LLMUserAggregator` and `UserTurnProcessor` are implemented using this controller.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a new foundational example `53-concurrent-llm-evaluation.py` that shows how to use `UserTurnProcessor`.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `should_interrupt` property to `DeepgramFluxSTTService`, `DeepgramSTTService`, and `SpeechmaticsSTTService` to configure whether the bot should be interrupted when the external service detects user speech.
|
||||
@@ -1,5 +0,0 @@
|
||||
- Smart Turn now takes into account `vad_start_seconds` when buffering audio,
|
||||
meaning that the start of the turn audio is not cut off. This improves
|
||||
accuracy for short utterances.
|
||||
|
||||
- The default value of `pre_speech_ms` is now set to 500ms for Smart Turn.
|
||||
@@ -1,4 +0,0 @@
|
||||
- `LLMAssistantAggregator` now exposes the following events:
|
||||
- `on_assistant_turn_started`: triggered when the assistant turn starts
|
||||
- `on_assistant_turn_stopped`: triggered when the assistant turn ends
|
||||
- `on_assistant_thought`: triggered when there's an assistant thought available
|
||||
@@ -1 +0,0 @@
|
||||
- `TranscriptProcessor` and related data classes and frames (`TranscriptionMessage`, `ThoughtTranscriptionMessage`, `TranscriptionUpdateFrame`) are deprecated. Use `LLMUserAggregator`'s and `LLMAssistantAggregator`'s new events (`on_user_turn_stopped` and `on_assistant_turn_stopped`) instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Added a new foundational example `28-user-assistant-turns.py` that shows how to use the new `LLMUserAggregator` and `LLMAssistantAggregator` events to gather a conversation transcript.
|
||||
@@ -1 +0,0 @@
|
||||
- Deprecated support for the `vad_events` `LiveOptions` in `DeepgramSTTService`. Instead, use a local Silero VAD for VAD events. Additionally, deprecated `should_interrupt` which will be removed along with `vad_events` support in a future release.
|
||||
@@ -1 +0,0 @@
|
||||
- Added `KrispVivaTurn` analyzer for end of turn detection using the Krisp VIVA SDK (requires `krisp_audio`).
|
||||
@@ -1 +0,0 @@
|
||||
- Improved Krisp SDK management to allow `KrispVivaTurn` and `KrispVivaFilter` to share a single SDK instance within the same process.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed potential memory leaks and initialization issues in `KrispVivaFilter` by improving SDK lifecycle management.
|
||||
@@ -1,6 +0,0 @@
|
||||
- Added support for setting up a pipeline task from external files. You can now register custom pipeline task setup files by setting the `PIPECAT_SETUP_FILES` environment variable. This variable should contain a colon-separated list of Python files (e.g. `export PIPECAT_SETUP_FILES="setup1.py:setup.py:..."`). Each file must define a function with the following signature:
|
||||
|
||||
```python
|
||||
async def setup_pipeline_task(task: PipelineTask):
|
||||
...
|
||||
```
|
||||
@@ -1 +0,0 @@
|
||||
- Loading external observers from files is deprecated, use the new pipeline task setup files and `PIPECAT_SETUP_FILES` environment variable instead.
|
||||
@@ -1 +0,0 @@
|
||||
- Updated default model for `GroqTTSService` to `canopylabs/orpheus-v1-english` and voice ID to `autumn`.
|
||||
@@ -1 +0,0 @@
|
||||
- Fixed timing issue in `BaseOutputTransport` where the bot speaking flag was set after awaiting, allowing the event loop to re-enter the method before the guard was set.
|
||||
@@ -1,16 +0,0 @@
|
||||
{% for section, _ in sections.items() %}
|
||||
{% if sections[section] %}
|
||||
{% for category, val in definitions.items() if category in sections[section]%}
|
||||
### {{ definitions[category]['name'] }}
|
||||
|
||||
{% for text, values in sections[section][category].items() %}
|
||||
{{ text }}
|
||||
(PR {{ values|join(', ') }})
|
||||
|
||||
{% endfor %}
|
||||
{% endfor %}
|
||||
{% else %}
|
||||
No significant changes.
|
||||
|
||||
{% endif %}
|
||||
{% endfor %}
|
||||
103
docs/TURN_AWARE_TRANSCRIPT_PROCESSOR.md
Normal file
103
docs/TURN_AWARE_TRANSCRIPT_PROCESSOR.md
Normal file
@@ -0,0 +1,103 @@
|
||||
# TurnAwareTranscriptProcessor Example
|
||||
|
||||
## Overview
|
||||
|
||||
The `TurnAwareTranscriptProcessor` combines user and assistant transcript tracking with turn boundary detection. It correctly handles interruptions by only capturing what was actually spoken.
|
||||
|
||||
## Basic Usage
|
||||
|
||||
```python
|
||||
from pipecat.processors.transcript_processor import TurnAwareTranscriptProcessor
|
||||
|
||||
# Create the processor
|
||||
turn_processor = TurnAwareTranscriptProcessor()
|
||||
|
||||
# Register event handlers
|
||||
@turn_processor.event_handler("on_turn_started")
|
||||
async def handle_turn_started(processor, turn_number):
|
||||
print(f"Turn {turn_number} started")
|
||||
|
||||
@turn_processor.event_handler("on_turn_ended")
|
||||
async def handle_turn_ended(processor, turn_number, user_text, assistant_text, was_interrupted):
|
||||
print(f"\nTurn {turn_number} ended:")
|
||||
print(f" User said: {user_text}")
|
||||
print(f" Assistant said: {assistant_text}")
|
||||
print(f" Was interrupted: {was_interrupted}")
|
||||
|
||||
@turn_processor.event_handler("on_transcript_update")
|
||||
async def handle_transcript_update(processor, frame):
|
||||
for msg in frame.messages:
|
||||
print(f"[{msg.role}]: {msg.content}")
|
||||
|
||||
# Add to pipeline
|
||||
pipeline = Pipeline([
|
||||
transport.input(),
|
||||
stt,
|
||||
turn_processor, # Process transcripts and track turns
|
||||
context_aggregator.user(),
|
||||
llm,
|
||||
tts,
|
||||
transport.output(),
|
||||
context_aggregator.assistant(),
|
||||
])
|
||||
```
|
||||
|
||||
## Features
|
||||
|
||||
1. **Turn Boundary Detection**: Automatically detects when turns start and end based on user and bot speaking patterns
|
||||
2. **Interruption Handling**: Correctly captures only what was actually spoken when interruptions occur
|
||||
3. **Real-time Transcripts**: Emits transcript messages for both user and assistant speech
|
||||
4. **Turn Events**: Provides start/end events with accumulated transcripts for each turn
|
||||
|
||||
## Events
|
||||
|
||||
### on_turn_started
|
||||
Emitted when a new turn begins (user starts speaking).
|
||||
|
||||
**Handler signature**: `async def handler(processor, turn_number)`
|
||||
|
||||
### on_turn_ended
|
||||
Emitted when a turn ends with accumulated transcripts.
|
||||
|
||||
**Handler signature**: `async def handler(processor, turn_number, user_transcript, assistant_transcript, was_interrupted)`
|
||||
|
||||
### on_transcript_update
|
||||
Inherited from `BaseTranscriptProcessor`, emitted for individual transcript messages.
|
||||
|
||||
**Handler signature**: `async def handler(processor, frame)`
|
||||
|
||||
## Turn Logic
|
||||
|
||||
- Turns start when the user begins speaking (`UserStartedSpeakingFrame`)
|
||||
- Turns end when:
|
||||
- The user starts speaking again (previous turn ends, new turn starts)
|
||||
- The bot is interrupted (`InterruptionFrame`)
|
||||
- The pipeline ends (`EndFrame`/`CancelFrame`)
|
||||
|
||||
## Integration with OpenTelemetry
|
||||
|
||||
You can use turn events to enrich OpenTelemetry spans:
|
||||
|
||||
```python
|
||||
from pipecat.utils.tracing.turn_trace_observer import TurnTraceObserver
|
||||
|
||||
turn_tracker = TurnTrackingObserver()
|
||||
turn_tracer = TurnTraceObserver(turn_tracker)
|
||||
turn_processor = TurnAwareTranscriptProcessor()
|
||||
|
||||
@turn_processor.event_handler("on_turn_ended")
|
||||
async def add_transcripts_to_span(processor, turn_number, user_text, assistant_text, interrupted):
|
||||
# Get current span and add transcript data
|
||||
from opentelemetry import trace
|
||||
current_span = trace.get_current_span()
|
||||
if current_span:
|
||||
current_span.set_attribute("turn.user_text", user_text)
|
||||
current_span.set_attribute("turn.assistant_text", assistant_text)
|
||||
```
|
||||
|
||||
## Notes
|
||||
|
||||
- The processor handles async frame processing correctly by delaying turn end until frames are processed
|
||||
- Works with word-level timestamps from TTS services like Cartesia
|
||||
- Accumulates both user (`TranscriptionFrame`) and assistant (`TTSTextFrame`) speech
|
||||
- Emits individual transcript messages in addition to turn-level aggregation
|
||||
@@ -2,7 +2,7 @@
|
||||
|
||||
# Build docs using uv
|
||||
echo "Installing dependencies with uv..."
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
uv sync --group docs --all-extras --no-extra krisp --no-extra gstreamer --no-extra ultravox --no-extra local_smart_turn --no-extra moondream --no-extra riva --no-extra mlx-whisper
|
||||
|
||||
# Check if sphinx-build is available
|
||||
if ! uv run sphinx-build --version &> /dev/null; then
|
||||
@@ -24,4 +24,4 @@ if [ $? -eq 0 ]; then
|
||||
else
|
||||
echo "Documentation build failed!" >&2
|
||||
exit 1
|
||||
fi
|
||||
fi
|
||||
@@ -61,6 +61,9 @@ autodoc_mock_imports = [
|
||||
# OpenCV - sometimes has import issues during docs build
|
||||
"cv2",
|
||||
# Heavy ML packages excluded from ReadTheDocs
|
||||
# ultravox dependencies
|
||||
"vllm",
|
||||
"vllm.engine.arg_utils",
|
||||
# local-smart-turn dependencies
|
||||
"coremltools",
|
||||
"coremltools.models",
|
||||
@@ -116,6 +119,7 @@ def import_core_modules():
|
||||
"pipecat.observers",
|
||||
"pipecat.runner",
|
||||
"pipecat.serializers",
|
||||
"pipecat.sync",
|
||||
"pipecat.transcriptions",
|
||||
"pipecat.utils",
|
||||
]
|
||||
|
||||
@@ -30,6 +30,7 @@ Quick Links
|
||||
Runner <api/pipecat.runner>
|
||||
Serializers <api/pipecat.serializers>
|
||||
Services <api/pipecat.services>
|
||||
Sync <api/pipecat.sync>
|
||||
Transcriptions <api/pipecat.transcriptions>
|
||||
Transports <api/pipecat.transports>
|
||||
Utils <api/pipecat.utils>
|
||||
Utils <api/pipecat.utils>
|
||||
12
env.example
12
env.example
@@ -73,9 +73,6 @@ GOOGLE_CLOUD_PROJECT_ID=...
|
||||
GOOGLE_CLOUD_LOCATION=...
|
||||
GOOGLE_TEST_CREDENTIALS=...
|
||||
|
||||
# Gradium
|
||||
GRAPDIUM_API_KEY=...
|
||||
|
||||
# Grok
|
||||
GROK_API_KEY=...
|
||||
|
||||
@@ -84,7 +81,6 @@ GROQ_API_KEY=...
|
||||
|
||||
# Heygen
|
||||
HEYGEN_API_KEY=...
|
||||
HEYGEN_LIVE_AVATAR_API_KEY=...
|
||||
|
||||
# Hume
|
||||
HUME_API_KEY=...
|
||||
@@ -97,8 +93,7 @@ INWORLD_API_KEY=...
|
||||
KRISP_MODEL_PATH=...
|
||||
|
||||
# Krisp Viva
|
||||
KRISP_VIVA_FILTER_MODEL_PATH=...
|
||||
KRISP_VIVA_TURN_MODEL_PATH=...
|
||||
KRISP_VIVA_MODEL_PATH=...
|
||||
|
||||
# LiveKit
|
||||
LIVEKIT_API_KEY=...
|
||||
@@ -192,11 +187,8 @@ TOGETHER_API_KEY=...
|
||||
TWILIO_ACCOUNT_SID=...
|
||||
TWILIO_AUTH_TOKEN=...
|
||||
|
||||
# Ultravox Realtime
|
||||
ULTRAVOX_API_KEY=...
|
||||
|
||||
# WhatsApp
|
||||
WHATSAPP_TOKEN=...
|
||||
WHATSAPP_WEBHOOK_VERIFICATION_TOKEN=...
|
||||
WHATSAPP_PHONE_NUMBER_ID=...
|
||||
WHATSAPP_APP_SECRET=...
|
||||
WHATSAPP_APP_SECRET=...
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -15,7 +15,7 @@ from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.nvidia.tts import NvidiaTTSService
|
||||
from pipecat.services.riva.tts import FastPitchTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
@@ -36,7 +36,7 @@ transport_params = {
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
tts = FastPitchTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -17,6 +17,7 @@ from fastapi.responses import RedirectResponse
|
||||
from loguru import logger
|
||||
from pipecat_ai_small_webrtc_prebuilt.frontend import SmallWebRTCPrebuiltUI
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -25,18 +26,13 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import TransportParams
|
||||
from pipecat.transports.smallwebrtc.connection import IceServer, SmallWebRTCConnection
|
||||
from pipecat.transports.smallwebrtc.transport import SmallWebRTCTransport
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -65,6 +61,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -85,14 +82,7 @@ async def run_example(webrtc_connection: SmallWebRTCConnection):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -12,6 +12,7 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -20,16 +21,11 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.daily import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.daily.transport import DailyParams, DailyTransport
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -50,6 +46,7 @@ async def main():
|
||||
audio_out_enabled=True,
|
||||
transcription_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -68,16 +65,7 @@ async def main():
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -12,6 +12,7 @@ import sys
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -26,17 +27,12 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -55,6 +51,7 @@ async def main():
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
)
|
||||
|
||||
@@ -78,14 +75,7 @@ async def main():
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -23,6 +23,7 @@ from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -26,6 +26,7 @@ from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.sync_parallel_pipeline import SyncParallelPipeline
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.aggregators.sentence import SentenceAggregator
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.services.cartesia.tts import CartesiaHttpTTSService
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -9,6 +9,7 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -23,10 +24,7 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -36,8 +34,6 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -70,16 +66,19 @@ transport_params = {
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -106,14 +105,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -10,6 +10,7 @@ from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
from PIL import Image
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -24,10 +25,7 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.processors.frame_processor import FrameDirection, FrameProcessor
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
@@ -36,8 +34,6 @@ from pipecat.services.deepgram.stt import DeepgramSTTService
|
||||
from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -88,6 +84,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
@@ -96,6 +93,7 @@ transport_params = {
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -120,14 +118,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -9,6 +9,7 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -17,10 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.stt import CartesiaSTTService
|
||||
@@ -29,8 +27,6 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -43,16 +39,19 @@ transport_params = {
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -77,14 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -9,6 +9,7 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -17,10 +18,7 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
@@ -29,8 +27,6 @@ from pipecat.services.openai.llm import OpenAILLMService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -42,16 +38,19 @@ transport_params = {
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -76,14 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -15,10 +15,10 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
@@ -29,7 +29,6 @@ from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_turn_strategies import ExternalUserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -77,7 +76,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
4. Text-to-Speech (TTS)
|
||||
- Low latency streaming audio synthesis
|
||||
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
|
||||
- Multiple voice options available including `sarah`, `theo`, and `megan`
|
||||
|
||||
5. Configuration Options
|
||||
- `operating_point` parameter defaults to `ENHANCED` for optimal accuracy
|
||||
@@ -96,8 +95,10 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
turn_detection_mode=SpeechmaticsSTTService.TurnDetectionMode.ADAPTIVE,
|
||||
# focus_speakers=["S1"],
|
||||
enable_vad=True,
|
||||
enable_diarization=True,
|
||||
focus_speakers=["S1"],
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
speaker_passive_format="<PASSIVE><{speaker_id}>{text}</{speaker_id}></PASSIVE>",
|
||||
),
|
||||
@@ -133,7 +134,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(user_turn_strategies=ExternalUserTurnStrategies()),
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -10,6 +10,7 @@ import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -18,10 +19,10 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
from pipecat.processors.aggregators.llm_response import (
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.openai.base_llm import BaseOpenAILLMService
|
||||
@@ -32,8 +33,6 @@ from pipecat.transcriptions.language import Language
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -45,16 +44,19 @@ transport_params = {
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -73,7 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
|
||||
TTS Features:
|
||||
- Low latency streaming audio synthesis
|
||||
- Multiple voice options available including `sarah`, `theo`, `megan` and `jack`
|
||||
- Multiple voice options available including `sarah`, `theo`, and `megan`
|
||||
|
||||
For more information:
|
||||
- STT: https://docs.speechmatics.com/rt-api-ref
|
||||
@@ -86,6 +88,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
api_key=os.getenv("SPEECHMATICS_API_KEY"),
|
||||
params=SpeechmaticsSTTService.InputParams(
|
||||
language=Language.EN,
|
||||
enable_diarization=True,
|
||||
end_of_utterance_silence_trigger=0.5,
|
||||
speaker_active_format="<{speaker_id}>{text}</{speaker_id}>",
|
||||
),
|
||||
)
|
||||
@@ -119,13 +123,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[
|
||||
TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())
|
||||
]
|
||||
),
|
||||
),
|
||||
user_params=LLMUserAggregatorParams(aggregation_timeout=0.005),
|
||||
)
|
||||
|
||||
pipeline = Pipeline(
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
# Copyright (c) 2024–2025, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
@@ -10,6 +10,7 @@ import os
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.audio.turn.smart_turn.base_smart_turn import SmartTurnParams
|
||||
from pipecat.audio.turn.smart_turn.local_smart_turn_v3 import LocalSmartTurnAnalyzerV3
|
||||
from pipecat.audio.vad.silero import SileroVADAnalyzer
|
||||
from pipecat.audio.vad.vad_analyzer import VADParams
|
||||
@@ -18,10 +19,7 @@ from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineParams, PipelineTask
|
||||
from pipecat.processors.aggregators.llm_context import LLMContext
|
||||
from pipecat.processors.aggregators.llm_response_universal import (
|
||||
LLMContextAggregatorPair,
|
||||
LLMUserAggregatorParams,
|
||||
)
|
||||
from pipecat.processors.aggregators.llm_response_universal import LLMContextAggregatorPair
|
||||
from pipecat.runner.types import RunnerArguments
|
||||
from pipecat.runner.utils import create_transport
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
@@ -30,8 +28,6 @@ from pipecat.services.soniox.stt import SonioxSTTService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
from pipecat.turns.user_stop import TurnAnalyzerUserTurnStopStrategy
|
||||
from pipecat.turns.user_turn_strategies import UserTurnStrategies
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
@@ -40,16 +36,19 @@ transport_params = {
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"twilio": lambda: FastAPIWebsocketParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
audio_in_enabled=True,
|
||||
audio_out_enabled=True,
|
||||
vad_analyzer=SileroVADAnalyzer(params=VADParams(stop_secs=0.2)),
|
||||
turn_analyzer=LocalSmartTurnAnalyzerV3(params=SmartTurnParams()),
|
||||
),
|
||||
}
|
||||
|
||||
@@ -76,14 +75,7 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
]
|
||||
|
||||
context = LLMContext(messages)
|
||||
context_aggregator = LLMContextAggregatorPair(
|
||||
context,
|
||||
user_params=LLMUserAggregatorParams(
|
||||
user_turn_strategies=UserTurnStrategies(
|
||||
stop=[TurnAnalyzerUserTurnStopStrategy(turn_analyzer=LocalSmartTurnAnalyzerV3())]
|
||||
),
|
||||
),
|
||||
)
|
||||
context_aggregator = LLMContextAggregatorPair(context)
|
||||
|
||||
pipeline = Pipeline(
|
||||
[
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user