wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Reorganize examples into topic-based subfolders

Browse Source 
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
2026-03-31 09:58:05 -04:00
parent f2ce7ececc
commit e719cbbe6d
307 changed files with 210 additions and 641 deletions
Download Patch File Download Diff File Expand all files Collapse all files

113
examples/README.md
View File

@@ -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).