Adrian Cowham
|
803ea9d8bc
|
update the canonical client so that the audio recording is optional as long as there is a transcript
|
2025-02-27 12:31:02 -08:00 |
|
Aleix Conchillo Flaqué
|
6722aae598
|
PipelineTask: force constructor keyword arguments
|
2025-02-25 18:58:47 -08:00 |
|
Aleix Conchillo Flaqué
|
7c13ec10d9
|
examples: cleanup ElevenLabsTTSService constructor arguments
|
2025-02-06 09:25:52 -08:00 |
|
Aleix Conchillo Flaqué
|
f3f22cf61c
|
AudioBufferProcessor: add start_recording()/stop_recording()
|
2025-02-01 11:06:58 -08:00 |
|
Aleix Conchillo Flaqué
|
3fe2124314
|
examples: use task.cancel() when participant leaves or disconnects
|
2025-01-28 15:46:20 -08:00 |
|
vatsal
|
dee1224530
|
Update runner.py
|
2025-01-23 13:21:49 +05:30 |
|
Adrian Cowham
|
d0b48c95bb
|
updated the example to use stereo audio and pass in the context. also updated the service to send the transcripts if they're available
|
2025-01-16 13:12:38 -08:00 |
|
Aleix Conchillo Flaqué
|
95e69597f3
|
update copyright keeping original year (2024)
|
2025-01-12 11:34:00 -08:00 |
|
Mark Backman
|
4d0c11fcab
|
Update examples to align with latest best practices
|
2025-01-10 15:07:06 -05:00 |
|
Mark Backman
|
4667624b60
|
Update copyright to 2025
|
2025-01-06 10:19:37 -05:00 |
|
Aleix Conchillo Flaqué
|
322dd0cea1
|
AudioBufferProcessor: use on_audio_data event handler to retrieve audio
|
2024-12-03 16:12:40 -08:00 |
|
vipyne
|
42cc79154f
|
docs: small fix
|
2024-10-29 14:33:57 -05:00 |
|
Aleix Conchillo Flaqué
|
b32448e967
|
transports(daily): make functions async
|
2024-10-25 15:01:52 -07:00 |
|
Vanessa Pyne
|
5321affda7
|
Merge pull request #588 from Allenmylath/patch-11
Update README.md
|
2024-10-21 11:20:05 -05:00 |
|
Aleix Conchillo Flaqué
|
b6b1ef0a40
|
Merge pull request #589 from Allenmylath/patch-12
Update Dockerfile
|
2024-10-20 10:59:43 -07:00 |
|
Aleix Conchillo Flaqué
|
dbfda14342
|
Merge pull request #587 from Allenmylath/patch-9
Update env.example
|
2024-10-20 10:58:50 -07:00 |
|
Aleix Conchillo Flaqué
|
fee85418cd
|
Merge pull request #620 from gregschwartz/main
Start agent/call/bot at localhost root
|
2024-10-20 10:14:10 -07:00 |
|
Aleix Conchillo Flaqué
|
be4bdabdf4
|
examples: use OpenAILLMContext in all the examples
|
2024-10-19 18:24:00 -07:00 |
|
Greg Schwartz
|
1fa52b62aa
|
Put start agent/call at localhost root. Before you had to read in the docs to go to /start, or /start_call or /start_bot. Which isn't mentioned in the console output, and is inconsistent, adding friction to learning the codebase
|
2024-10-19 16:18:43 -07:00 |
|
Aleix Conchillo Flaqué
|
2a37b2459a
|
move vad package to audio.vad
|
2024-10-17 13:49:16 -07:00 |
|
allenmylath
|
ec98a13a08
|
Update Dockerfile
utils and assets not used in this example hence removed
|
2024-10-15 08:18:16 +05:30 |
|
allenmylath
|
b999b76f70
|
Update README.md
readme description still shows simple-chatbot definition hence made more accurate description
|
2024-10-15 08:14:43 +05:30 |
|
allenmylath
|
b64dbe7bb4
|
Update env.example
canonical api url is also used from env.
|
2024-10-15 08:10:07 +05:30 |
|
Adrian Cowham
|
79c8aa2c4a
|
ruff formatting
|
2024-10-11 11:35:02 -07:00 |
|
Adrian Cowham
|
522d931950
|
better interruption handling by moving the processors after the transport output
|
2024-10-11 10:33:12 -07:00 |
|
Adrian Cowham
|
4d81a2ebfe
|
nuked the code that marks user audio in favor for InputAudioRawFrame. also moving to stereo instead of mono with the human and bot on their own channel.
|
2024-10-03 14:10:03 -07:00 |
|
Adrian Cowham
|
2e02ab740d
|
PR feedback
|
2024-09-15 20:59:17 -07:00 |
|
Adrian Cowham
|
f411bf33fd
|
adding a frame processor with the ability to save a conversation to a buffer and another frame processor to upload audio to Canonical for evaluation and metrics collection. Examples included
|
2024-09-10 10:15:48 -07:00 |
|