Kwindla Hultman Kramer ddfd721f6e openai tts ttfb

2024-06-06 11:32:47 -04:00

..

assets

move src/examples to examples

2024-03-18 11:51:38 -07:00

01-say-one-thing.py

initial commit for new pipecat architecture

2024-05-12 10:07:25 -07:00

01a-local-audio.py

examples: use LocalAudioTransport

2024-05-12 10:07:54 -07:00

02-llm-say-one-thing.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

03-still-frame.py

initial commit for new pipecat architecture

2024-05-12 10:07:25 -07:00

03a-local-still-frame.py

initial commit for new pipecat architecture

2024-05-12 10:07:25 -07:00

04-utterance-and-speech.py

initial commit for new pipecat architecture

2024-05-12 10:07:25 -07:00

05-sync-speech-and-image.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

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

pipeline(task): introduce has_finished()

2024-06-04 15:43:54 -07:00

06-listen-and-respond.py

Function calling (#175)

2024-05-30 12:25:39 -05:00

06a-image-sync.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

07-interruptible.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

07a-interruptible-anthropic.py

introduce PipelineParams

2024-05-28 17:14:14 -07:00

07b-interruptible-langchain.py

pyproject: include langchain-community and langchain-openai

2024-06-04 15:43:54 -07:00

07c-interruptible-deepgram.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

07d-interruptible-cartesia.py

cartesia async fixed

2024-06-06 11:24:26 -04:00

07e-interruptible-playht.py

cartesia async fixed

2024-06-06 11:24:26 -04:00

07g-interruptible-openai-tts.py

openai tts ttfb

2024-06-06 11:32:47 -04:00

08-bots-arguing.py

go back to using @dataclass since they can be inspected

2024-05-12 22:35:43 -07:00

09-mirror.py

examples: use camera_out_is_live for live video

2024-06-04 15:43:54 -07:00

09a-local-mirror.py

pipeline(task): introduce has_finished()

2024-06-04 15:43:54 -07:00

10-wake-phrase.py

Function calling (#175)

2024-05-30 12:25:39 -05:00

11-sound-effects.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

12-describe-video.py

examples: pipelines readability and add LLM assistants after transport

2024-05-17 14:52:51 -07:00

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

services(google): make api_key argument mandatory

2024-05-24 09:23:00 -07:00

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

examples: no need to define tts twice

2024-05-24 09:23:00 -07:00

12c-describe-video-anthropic.py

examples: no need to define tts twice

2024-05-24 09:23:00 -07:00

13-whisper-transcription.py

initial commit for new pipecat architecture

2024-05-12 10:07:25 -07:00

13a-whisper-local.py

examples: use camera_out_is_live for live video

2024-06-04 15:43:54 -07:00

14-function-calling.py

examples: use gpt-4o model by default

2024-05-31 11:36:52 -07:00

runner.py

examples: copy runner.py and auth.py where needed

2024-03-18 17:10:23 -07:00