pipecat

assets

added an example using using Gemini's large context window for RAG

2025-02-06 12:49:29 -08:00

01-say-one-thing.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

01a-local-audio.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

01b-livekit-audio.py

fix ruff linter import organization

2024-12-17 11:28:58 -08:00

01c-fastpitch.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

02-llm-say-one-thing.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

03-still-frame.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

03a-local-still-frame.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

03b-still-frame-imagen.py

More Storybot updates (#1116 )

2025-01-30 20:13:18 -06:00

04-utterance-and-speech.py

examples: cleanup ElevenLabsTTSService constructor arguments

2025-02-06 09:25:52 -08:00

05-sync-speech-and-image.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

05a-local-sync-speech-and-image.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

06-listen-and-respond.py

add missing super().process_frame() calls

2025-01-30 13:15:17 -08:00

06a-image-sync.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07-interruptible-vad.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07-interruptible.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07a-interruptible-anthropic.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07b-interruptible-langchain.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07c-interruptible-deepgram-vad.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07c-interruptible-deepgram.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07d-interruptible-elevenlabs.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07e-interruptible-playht-http.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07e-interruptible-playht.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07f-interruptible-azure.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07g-interruptible-openai.py

Add an example for Whisper using OpenAI API

2025-02-04 10:32:55 +09:00

07h-interruptible-openpipe.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07i-interruptible-xtts.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07j-interruptible-gladia.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07k-interruptible-lmnt.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

07l-interruptible-together.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07m-interruptible-polly.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07n-interruptible-google.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

07o-interruptible-assemblyai.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07p-interruptible-krisp.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07q-interruptible-rime.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07r-interruptible-riva-nim.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

07s-interruptible-google-audio-in.py

Use gemini-2.0-flash-001 as the default model for GoogleLLMService

2025-02-06 12:29:15 -05:00

07t-interruptible-fish.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

08-bots-arguing.py

examples: cleanup ElevenLabsTTSService constructor arguments

2025-02-06 09:25:52 -08:00

09-mirror.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

09a-local-mirror.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

10-wake-phrase.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

11-sound-effects.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

12-describe-video.py

prefer Optional over to "| None"

2025-02-06 11:11:37 -08:00

12a-describe-video-gemini-flash.py

prefer Optional over to "| None"

2025-02-06 11:11:37 -08:00

12b-describe-video-gpt-4o.py

prefer Optional over to "| None"

2025-02-06 11:11:37 -08:00

12c-describe-video-anthropic.py

prefer Optional over to "| None"

2025-02-06 11:11:37 -08:00

13-whisper-transcription.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

13a-whisper-local.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

13b-deepgram-transcription.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

13c-gladia-transcription.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

13d-assemblyai-transcription.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

14-function-calling.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14a-function-calling-anthropic.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

14b-function-calling-anthropic-video.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

14c-function-calling-together.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14d-function-calling-video.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

14e-function-calling-gemini.py

Use gemini-2.0-flash-001 as the default model for GoogleLLMService

2025-02-06 12:29:15 -05:00

14f-function-calling-groq.py

Add GroqSTTService, BaseWhisperSTTService, and refactor OpenAISTTService

2025-02-09 07:51:28 -05:00

14g-function-calling-grok.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14h-function-calling-azure.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14i-function-calling-fireworks.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14j-function-calling-nim.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14k-function-calling-cerebras.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14l-function-calling-deepseek.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14m-function-calling-openrouter.py

examples: update 14 series with TTSSpeakFrame

2025-01-27 14:42:23 -08:00

14n-function-calling-perplexity.py

Add PerplexityLLMService

2025-02-09 08:00:31 -05:00

15-switch-voices.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

15a-switch-languages.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

16-gpu-container-local-bot.py

update copyright keeping original year (2024)

2025-01-12 11:34:00 -08:00

17-detect-user-idle.py

Added retry functionality and a new callback to the UserIdleProcessor

2025-01-27 10:24:57 -05:00

18-gstreamer-filesrc.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

18a-gstreamer-videotestsrc.py

2025-01-12 11:34:00 -08:00

19-openai-realtime-beta.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

20a-persistent-context-openai.py

2025-01-12 11:34:00 -08:00

20b-persistent-context-openai-realtime.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

20c-persistent-context-anthropic.py

2025-01-12 11:34:00 -08:00

20d-persistent-context-gemini.py

Use gemini-2.0-flash-001 as the default model for GoogleLLMService

2025-02-06 12:29:15 -05:00

21-tavus-layer.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

22-natural-conversation.py

examples: fix 22 series initial gate state

2025-02-03 09:16:58 -08:00

22b-natural-conversation-proposal.py

Update foundation examples 22b, 22c, and 22d to be ready for function calling

2025-02-06 15:36:16 -05:00

22c-natural-conversation-mixed-llms.py

Update foundation examples 22b, 22c, and 22d to be ready for function calling

2025-02-06 15:36:16 -05:00

22d-natural-conversation-gemini-audio.py

Update foundation examples 22b, 22c, and 22d to be ready for function calling

2025-02-06 15:36:16 -05:00

23-bot-background-sound.py

2025-01-12 11:34:00 -08:00

24-stt-mute-filter.py

Deprecate stt_service parameter in STTMuteFilter

2025-02-07 19:24:03 -05:00

25-google-audio-in.py

Use gemini-2.0-flash-001 as the default model for GoogleLLMService

2025-02-06 12:29:15 -05:00

26-gemini-multimodal-live.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

26a-gemini-multimodal-live-transcription.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

26b-gemini-multimodal-live-function-calling.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

26c-gemini-multimodal-live-video.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

26d-gemini-multimodal-live-text.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

26e-gemini-multimodal-google-search.py

Fixing ruff format

2025-01-10 13:21:51 -03:00

27-simli-layer.py

2025-01-12 11:34:00 -08:00

28a-transcription-processor-openai.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

28b-transcript-processor-anthropic.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

28c-transcription-processor-gemini.py

Update 28c option to output to log line only by default

2025-02-08 10:00:45 -05:00

29-livekit-audio-chat.py

introduce PipelineParams audio input/output sample rates

2025-02-04 14:12:56 -08:00

30-observer.py

examples: use task.cancel() when participant leaves or disconnects

2025-01-28 15:46:20 -08:00

31-heartbeats.py

examples: add 31-heartbeats.py

2025-01-16 19:31:13 -08:00

32-gemini-grounding-metadata.py

Export .rtvi, update new-chatbot example, rename and update foundational 32

2025-02-07 09:15:32 -08:00

33-gemini-rag.py

PR feedback: renamed file, added docstring, changed file read logic

2025-02-10 09:39:01 -08:00

runner.py

prefer Optional over to "| None"

2025-02-06 11:11:37 -08:00