Reorganize examples into topic-based subfolders
Move 304 examples from a flat numbered directory into 14 descriptive subfolders: getting-started, services (speech + function-calling), transcription, vision, realtime, persistent-context, context-summarization, update-settings (stt/tts/llm), turn-management, thinking-and-mcp, transports, video-avatar, video-processing, and features. Strip numbered prefixes from filenames (e.g. 07c-interruptible-deepgram.py becomes services/speech/deepgram.py) since the folder context makes them redundant. Keep numbered prefixes only in getting-started/ where ordering matters. Update eval script paths and README to match the new structure.
This commit is contained in:
Mark Backman
@@ -80,7 +80,7 @@ Catch new features, interviews, and how-tos on our [Pipecat TV](https://www.yout
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/storytelling-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/storytelling-chatbot/image.png" width="400" /></a>
|
||||
<br/>
|
||||
<a href="https://github.com/pipecat-ai/pipecat-examples/tree/main/translation-chatbot"><img src="https://raw.githubusercontent.com/pipecat-ai/pipecat-examples/main/translation-chatbot/image.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/12-describe-video.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/assets/moondream.png" width="400" /></a>
|
||||
<a href="https://github.com/pipecat-ai/pipecat/blob/main/examples/vision/moondream.py"><img src="https://github.com/pipecat-ai/pipecat/blob/main/examples/assets/moondream.png" width="400" /></a>
|
||||
</p>
|
||||
|
||||
## 🧩 Available services
|
||||
|
||||
@@ -1,71 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
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.piper.tts import PiperHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = PiperHttpTTSService(
|
||||
base_url=os.getenv("PIPER_BASE_URL"),
|
||||
aiohttp_session=session,
|
||||
sample_rate=24000,
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,72 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
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.rime.tts import RimeHttpTTSService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
tts = RimeHttpTTSService(
|
||||
api_key=os.getenv("RIME_API_KEY", ""),
|
||||
aiohttp_session=session,
|
||||
settings=RimeHttpTTSService.Settings(
|
||||
voice="rex",
|
||||
),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,64 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import asyncio
|
||||
import os
|
||||
import sys
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
from pipecat.pipeline.runner import PipelineRunner
|
||||
from pipecat.pipeline.task import PipelineTask
|
||||
from pipecat.runner.livekit import configure
|
||||
from pipecat.services.cartesia.tts import CartesiaTTSService
|
||||
from pipecat.transports.livekit.transport import LiveKitParams, LiveKitTransport
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
logger.remove(0)
|
||||
logger.add(sys.stderr, level="DEBUG")
|
||||
|
||||
|
||||
async def main():
|
||||
(url, token, room_name) = await configure()
|
||||
|
||||
transport = LiveKitTransport(
|
||||
url=url,
|
||||
token=token,
|
||||
room_name=room_name,
|
||||
params=LiveKitParams(audio_out_enabled=True),
|
||||
)
|
||||
|
||||
tts = CartesiaTTSService(
|
||||
api_key=os.getenv("CARTESIA_API_KEY"),
|
||||
settings=CartesiaTTSService.Settings(
|
||||
voice="71a7ad14-091c-4e8e-a314-022ece01c121", # British Reading Lady
|
||||
),
|
||||
)
|
||||
|
||||
runner = PipelineRunner()
|
||||
|
||||
task = PipelineTask(Pipeline([tts, transport.output()]))
|
||||
|
||||
# Register an event handler so we can play the audio when the
|
||||
# participant joins.
|
||||
@transport.event_handler("on_first_participant_joined")
|
||||
async def on_first_participant_joined(transport, participant_id):
|
||||
await asyncio.sleep(1)
|
||||
await task.queue_frame(
|
||||
TTSSpeakFrame(
|
||||
"Hello there! How are you doing today? Would you like to talk about the weather?"
|
||||
)
|
||||
)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
asyncio.run(main())
|
||||
@@ -1,64 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import EndFrame, TTSSpeakFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
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.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
from pipecat.transports.websocket.fastapi import FastAPIWebsocketParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(audio_out_enabled=True),
|
||||
"twilio": lambda: FastAPIWebsocketParams(audio_out_enabled=True),
|
||||
"webrtc": lambda: TransportParams(audio_out_enabled=True),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
tts = NvidiaTTSService(api_key=os.getenv("NVIDIA_API_KEY"))
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([tts, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frames([TTSSpeakFrame(f"Hello there!"), EndFrame()])
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,84 +0,0 @@
|
||||
#
|
||||
# Copyright (c) 2024-2026, Daily
|
||||
#
|
||||
# SPDX-License-Identifier: BSD 2-Clause License
|
||||
#
|
||||
|
||||
import os
|
||||
|
||||
import aiohttp
|
||||
from dotenv import load_dotenv
|
||||
from loguru import logger
|
||||
|
||||
from pipecat.frames.frames import TextFrame
|
||||
from pipecat.pipeline.pipeline import Pipeline
|
||||
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.fal.image import FalImageGenService
|
||||
from pipecat.transports.base_transport import BaseTransport, TransportParams
|
||||
from pipecat.transports.daily.transport import DailyParams
|
||||
|
||||
load_dotenv(override=True)
|
||||
|
||||
|
||||
# We use lambdas to defer transport parameter creation until the transport
|
||||
# type is selected at runtime.
|
||||
transport_params = {
|
||||
"daily": lambda: DailyParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
"webrtc": lambda: TransportParams(
|
||||
video_out_enabled=True,
|
||||
video_out_width=1024,
|
||||
video_out_height=1024,
|
||||
),
|
||||
}
|
||||
|
||||
|
||||
async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
logger.info(f"Starting bot")
|
||||
|
||||
# Create an HTTP session
|
||||
async with aiohttp.ClientSession() as session:
|
||||
imagegen = FalImageGenService(
|
||||
settings=FalImageGenService.Settings(
|
||||
image_size="square_hd",
|
||||
),
|
||||
aiohttp_session=session,
|
||||
key=os.getenv("FAL_KEY"),
|
||||
)
|
||||
|
||||
task = PipelineTask(
|
||||
Pipeline([imagegen, transport.output()]),
|
||||
idle_timeout_secs=runner_args.pipeline_idle_timeout_secs,
|
||||
)
|
||||
|
||||
# Register an event handler so we can play the audio when the client joins
|
||||
@transport.event_handler("on_client_connected")
|
||||
async def on_client_connected(transport, client):
|
||||
await task.queue_frame(TextFrame("a cat in the style of picasso"))
|
||||
|
||||
@transport.event_handler("on_client_disconnected")
|
||||
async def on_client_disconnected(transport, client):
|
||||
logger.info(f"Client disconnected")
|
||||
await task.cancel()
|
||||
|
||||
runner = PipelineRunner(handle_sigint=runner_args.handle_sigint)
|
||||
|
||||
await runner.run(task)
|
||||
|
||||
|
||||
async def bot(runner_args: RunnerArguments):
|
||||
"""Main bot entry point compatible with Pipecat Cloud."""
|
||||
transport = await create_transport(runner_args, transport_params)
|
||||
await run_bot(transport, runner_args)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
from pipecat.runner.run import main
|
||||
|
||||
main()
|
||||
@@ -1,6 +1,6 @@
|
||||
# Pipecat Examples
|
||||
|
||||
This directory contains examples showing how to build voice and multimodal agents with Pipecat. Each example demonstrates specific features, progressing from basic to advanced concepts.
|
||||
This directory contains examples showing how to build voice and multimodal agents with Pipecat.
|
||||
|
||||
## Setup
|
||||
|
||||
@@ -17,19 +17,13 @@ This directory contains examples showing how to build voice and multimodal agent
|
||||
# Edit .env with your API keys
|
||||
```
|
||||
|
||||
3. Navigate to the examples directory if you aren't already there:
|
||||
3. Run any example:
|
||||
|
||||
```bash
|
||||
cd examples
|
||||
uv run python getting-started/01-say-one-thing.py
|
||||
```
|
||||
|
||||
4. Run any example:
|
||||
|
||||
```bash
|
||||
uv run python 01-say-one-thing.py
|
||||
```
|
||||
|
||||
5. Open the web interface at http://localhost:7860/client/ and click "Connect"
|
||||
4. Open the web interface at http://localhost:7860/client/ and click "Connect"
|
||||
|
||||
## Running examples with other transports
|
||||
|
||||
@@ -40,7 +34,7 @@ Most examples support running with other transports, like Twilio or Daily.
|
||||
You need to create a Daily account at https://dashboard.daily.co/u/signup. Once signed up, you can create your own room from the dashboard and set the environment variables `DAILY_ROOM_URL` and `DAILY_API_KEY`. Alternatively, you can let the example create a room for you (still needs `DAILY_API_KEY` environment variable). Then, start any example with `-t daily`:
|
||||
|
||||
```bash
|
||||
uv run 07-interruptible.py -t daily
|
||||
uv run getting-started/06-voice-agent.py -t daily
|
||||
```
|
||||
|
||||
### Twilio
|
||||
@@ -58,74 +52,73 @@ ngrok http 7860
|
||||
Then, run the example with:
|
||||
|
||||
```bash
|
||||
uv run 07-interruptible.py -t twilio -x NGROK_HOST_NAME
|
||||
uv run getting-started/06-voice-agent.py -t twilio -x NGROK_HOST_NAME
|
||||
```
|
||||
|
||||
## Examples by Feature
|
||||
## Directory Structure
|
||||
|
||||
### Basics
|
||||
### [`getting-started/`](./getting-started/)
|
||||
|
||||
- **[01-say-one-thing.py](./01-say-one-thing.py)**: Most basic bot that says one phrase and exits (Transport, TTS, Event handlers)
|
||||
- **[02-llm-say-one-thing.py](./02-llm-say-one-thing.py)**: Bot generates a response with an LLM (LLM initialization)
|
||||
- **[03-still-frame.py](./03-still-frame.py)**: Displays a static image (Video transport, Image service)
|
||||
- **[04-transport.py](./04-transport.py)**: Different transport options (WebRTC, Daily, Livekit)
|
||||
Progressive introduction to Pipecat, from minimal TTS to a full voice agent with function calling.
|
||||
|
||||
### Conversational AI
|
||||
### [`services/`](./services/)
|
||||
|
||||
- **[07-interruptible.py](./07-interruptible.py)**: Basic voice assistant bot (STT, TTS, LLM, Interruptible speech)
|
||||
- **[10-wake-phrase.py](./10-wake-phrase.py)**: Bot activated by wake phrase (WakeCheckFilter)
|
||||
- **[22-natural-conversation.py](./22-natural-conversation.py)**: Smart turn detection (Multiple LLMs, Turn management)
|
||||
- **[38-smart-turn-fal.py](./38-smart-turn-fal.py)**: ML-based turn detection (Fal service, Local models)
|
||||
Service provider integration examples, organized into subfolders:
|
||||
|
||||
### Common Utilities
|
||||
- **[`speech/`](./services/speech/)** — Full STT + LLM + TTS pipelines showcasing different speech service providers (Deepgram, ElevenLabs, Cartesia, etc.)
|
||||
- **[`function-calling/`](./services/function-calling/)** — Function calling with different LLM providers (OpenAI, Anthropic, Google, etc.)
|
||||
|
||||
- **[17-detect-user-idle.py](./17-detect-user-idle.py)**: Handle inactive users (UserIdleProcessor)
|
||||
- **[24-user-mute-strategy.py](./24-user-mute-strategy.py)**: Selectively mute user input (LLMUserAggregator user mute strategies)
|
||||
- **[28-transcription-processor.py](./28-transcription-processor.py)**: Record conversation text (TranscriptProcessor)
|
||||
- **[30-observer.py](./30-observer.py)**: Access frame data (Custom observers)
|
||||
- **[31-heartbeats.py](./31-heartbeats.py)**: Detect idle pipelines (Pipeline monitoring)
|
||||
- **[34-audio-recording.py](./34-audio-recording.py)**: Record conversation audio (Composite and track-level recording)
|
||||
### [`transcription/`](./transcription/)
|
||||
|
||||
### Advanced LLM Features
|
||||
Speech-to-text examples with various STT providers.
|
||||
|
||||
- **[14-function-calling.py](./14-function-calling.py)**: Bot with tool usage (Function schemas, Tool registration)
|
||||
- **[20a-persistent-context-openai.py](./20a-persistent-context-openai.py)**: Persistent conversation context (Memory management)
|
||||
- **[32-gemini-grounding-metadata.py](./32-gemini-grounding-metadata.py)**: Web search capabilities (Google search integration)
|
||||
- **[33-gemini-rag.py](./33-gemini-rag.py)**: Retrieval-augmented generation (Data sources, Grounding)
|
||||
- **[37-mem0.py](./37-mem0.py)**: Long-term agent memory (Mem0 service integration)
|
||||
### [`vision/`](./vision/)
|
||||
|
||||
### Media Handling
|
||||
Image description and vision capabilities with different multimodal LLMs.
|
||||
|
||||
- **[05-sync-speech-and-images.py](./05-sync-speech-and-images.py)**: Synchronized narration with images (Custom processors, SyncParallelPipeline)
|
||||
- **[06a-image-sync.py](./06a-image-sync.py)**: Dynamic image updates while speaking (Synchronized A/V pipelines)
|
||||
- **[09-mirror.py](./09-mirror.py)**: Mirror user's audio and video (Custom frame processors)
|
||||
- **[11-sound-effects.py](./11-sound-effects.py)**: Add sounds when bot speaks (Sound playback, Event synchronization)
|
||||
- **[23-bot-background-sound.py](./23-bot-background-sound.py)**: Play background audio (SoundfileMixer)
|
||||
### [`realtime/`](./realtime/)
|
||||
|
||||
### Vision & Multimodal
|
||||
Realtime and multimodal live APIs (OpenAI Realtime, Gemini Live, AWS Nova Sonic, Ultravox, Grok).
|
||||
|
||||
- **[12a-describe-video-gemini-flash.py](./12a-describe-video-gemini-flash.py)**: Bot describes user's video (Video input, Multimodal LLMs)
|
||||
- **[26c-gemini-live-video.py](./26c-gemini-live-video.py)**: Gemini with video input (Streaming video, Function calls)
|
||||
### [`persistent-context/`](./persistent-context/)
|
||||
|
||||
### Voice & Language
|
||||
Maintaining conversation context across sessions with different providers.
|
||||
|
||||
- **[13-transcription.py](./13-transcription.py)**: Speech transcription demo (STT providers, Real-time transcription)
|
||||
- **[15-switch-voices.py](./15-switch-voices.py)**: Dynamic voice/language changing (ParallelPipelines, FunctionFilters)
|
||||
- **[25-google-audio-in.py](./25-google-audio-in.py)**: Gemini for speech recognition (Alternative transcription)
|
||||
- **[35-pattern-pair-voice-switching.py](./35-pattern-pair-voice-switching.py)**: Dynamic TTS voice switching (XML parsing, PatternPairAggregator)
|
||||
- **[36-user-email-gathering.py](./36-user-email-gathering.py)**: Spelling mode for TTS (Confirmation patterns, XML tags)
|
||||
### [`context-summarization/`](./context-summarization/)
|
||||
|
||||
### Integration Examples
|
||||
Summarizing conversation context to manage token limits.
|
||||
|
||||
- **[18-gstreamer-filesrc.py](./18-gstreamer-filesrc.py)**: GStreamer video streaming (Video processing)
|
||||
- **[19-openai-realtime-beta.py](./19-openai-realtime-beta.py)**: OpenAI Speech-to-Speech (Direct S2S, Function calls)
|
||||
- **[21-tavus-layer-tavus-transport.py](./21-tavus-layer-tavus-transport.py)**: Tavus digital twin (Avatar integration)
|
||||
- **[27-simli-layer.py](./27-simli-layer.py)**: Simli avatar integration (Video synchronization)
|
||||
- **[56-lemonslice-transport.py](./56-lemonslice-transport.py)**: LemonSlice avatar integration (A/V Synced Avatar integration)
|
||||
### [`update-settings/`](./update-settings/)
|
||||
|
||||
### Performance & Optimization
|
||||
Changing service settings at runtime, organized by service type:
|
||||
|
||||
- **[16-gpu-container-local-bot.py](./16-gpu-container-local-bot.py)**: GPU-accelerated local bot (Performance measurement)
|
||||
- **[`stt/`](./update-settings/stt/)** — Speech-to-text settings
|
||||
- **[`tts/`](./update-settings/tts/)** — Text-to-speech settings
|
||||
- **[`llm/`](./update-settings/llm/)** — LLM settings
|
||||
|
||||
### [`turn-management/`](./turn-management/)
|
||||
|
||||
Turn detection, interruption handling, and user input management.
|
||||
|
||||
### [`thinking-and-mcp/`](./thinking-and-mcp/)
|
||||
|
||||
LLM thinking/reasoning modes and MCP (Model Context Protocol) tool server integration.
|
||||
|
||||
### [`transports/`](./transports/)
|
||||
|
||||
Transport layer examples (WebRTC, Daily, LiveKit).
|
||||
|
||||
### [`video-avatar/`](./video-avatar/)
|
||||
|
||||
Video avatar integrations (Tavus, HeyGen, Simli, LemonSlice).
|
||||
|
||||
### [`video-processing/`](./video-processing/)
|
||||
|
||||
Video processing, mirroring, GStreamer, and custom video tracks.
|
||||
|
||||
### [`features/`](./features/)
|
||||
|
||||
Miscellaneous features: sound effects, wake phrases, observers, audio recording, live translation, service switching, and more.
|
||||
|
||||
## Advanced Usage
|
||||
|
||||
@@ -141,4 +134,4 @@ uv run python <example-name> --host 0.0.0.0 --port 8080
|
||||
- **Connection errors**: Verify API keys in `.env` file
|
||||
- **Port conflicts**: Use `--port` to change the port
|
||||
|
||||
For more examples, visit our the [pipecat-examples repository](https://github.com/pipecat-ai/pipecat-examples).
|
||||
For more examples, visit the [pipecat-examples repository](https://github.com/pipecat-ai/pipecat-examples).
|
||||
|
||||
@@ -119,8 +119,8 @@ async def run_bot(transport: BaseTransport, runner_args: RunnerArguments):
|
||||
)
|
||||
|
||||
image_sync_aggregator = ImageSyncAggregator(
|
||||
os.path.join(os.path.dirname(__file__), "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "assets", "waiting.png"),
|
||||
os.path.join(os.path.dirname(__file__), "..", "assets", "speaking.png"),
|
||||
os.path.join(os.path.dirname(__file__), "..", "assets", "waiting.png"),
|
||||
)
|
||||
|
||||
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