Ben Xu
|
f68f83c6ba
|
update local and default profile
|
10 months ago |
|
Ben Xu
|
4c271b19a7
|
remove separate transcriptions
|
10 months ago |
|
Ben Xu
|
6110e70430
|
add local stt & tts, add anticipation logic, remove video context accumulation
|
10 months ago |
|
Ben Xu
|
6084e2591a
|
refactor logging outside logic
|
10 months ago |
|
Ben Xu
|
095b704da4
|
add basic interrupt logic
|
10 months ago |
|
Ben Xu
|
4e77a5792f
|
remove duplicate fnc_ctx declaration
|
10 months ago |
|
Ben Xu
|
8f6d5fdac7
|
remove assistant fnc
|
10 months ago |
|
Ben Xu
|
bba33db0c6
|
update server to use new interpreter
|
10 months ago |
|
Ben Xu
|
c2de04ab63
|
update profiles to be compatible with new interpreter
|
10 months ago |
|
Ben Xu
|
178ffc83bd
|
update logging with debug env variable
|
10 months ago |
|
Ben Xu
|
07672f498b
|
add voice assistant state communication and clear chat context
|
10 months ago |
|
Ben Xu
|
f6c13a13bd
|
send multimodal message on startup of multimodal agent
|
10 months ago |
ben
|
1720b783ce
|
LiveKit Pipeline Agent (#4)
* init processors
* fix image append for chat messages
* add pre tts cb
* stash non-functional worker changes
* add complete flag parsing worker
* stash worker changes
* update worker.py to handle message context correctly
* draft worker -- currently mismanages chat ctx
* stash draft delta changes
* working worker on push to talk happy path
* final working worker on push to talk
* refactor append image
* updated video frame processing
* rm text processor
* working draft main
* draft working poetry
|
11 months ago |
killian
|
befddaf205
|
Cartesia
|
12 months ago |
|
killian
|
a5b6948c9c
|
Multimodal code execution
|
12 months ago |
|
Ben Xu
|
21e04c18fe
|
isolate instruction update
|
1 year ago |
|
Ben Xu
|
35b1c5caa2
|
Revert "update instructions"
This reverts commit 9c145d0209.
|
1 year ago |
|
Ben Xu
|
9c145d0209
|
update instructions
|
1 year ago |
|
Ben Xu
|
121e67e896
|
Revert "process custom flags on worker"
This reverts commit 12efc95688.
|
1 year ago |
|
Ben Xu
|
5810db4692
|
init livekit quickstart multimodal worker
|
1 year ago |
|
Ben Xu
|
12efc95688
|
process custom flags on worker
|
1 year ago |
|
killian
|
197417a65b
|
Default tts to elevenlabs
|
1 year ago |
|
killian
|
393d127540
|
Turn off debugging
|
1 year ago |
|
killian
|
b3ebbabcf1
|
Change tts and stt from profiles for app, set context mode to be True at the start
|
1 year ago |
|
killian
|
81242d8568
|
Change tts and stt from profiles for app, set context mode to be True at the start
|
1 year ago |
|
killian
|
a0d1e7038b
|
`01.1`
|
1 year ago |
|
killian
|
4aec113c41
|
`01.1` (Later Tonight)
|
1 year ago |
|
killian
|
1839cc6e74
|
Better default profile, better QR
|
1 year ago |
|
killian
|
f4d9cd39e7
|
OpenAI TTS and worker retry logic
|
1 year ago |
|
killian
|
927fba85a6
|
OpenAI TTS
|
1 year ago |
|
killian
|
bb53f9f81f
|
Change worker to be a python file
|
1 year ago |
|
killian
|
6fb71dde41
|
Docs changes, minor fixes
|
1 year ago |
|
killian
|
51c8206c57
|
Fixing auth
|
1 year ago |
|
killian
|
36f765c4d1
|
Bumped OI and fixed auth
|
1 year ago |
|
killian
|
a7f381cb36
|
01.1
|
1 year ago |
|
killian
|
52d88fd72c
|
Cleaned up starting logic
|
1 year ago |
|
Ben Xu
|
a595bdf570
|
consolidate tunneling to ngrok service
|
1 year ago |
|
killian
|
d4259759d1
|
Docs overhaul
[WIP] Improve docs
|
1 year ago |
Mike Bird
|
d1989027ef
|
update default profile
|
1 year ago |
|
killian
|
93f635b915
|
Changed tests, remove acknowledge requirement
|
1 year ago |
|
Mike Bird
|
5fabfb06f0
|
Expand the configuration guide with examples and instructions on using custom profiles, including TTS provider setup
|
1 year ago |
|
killian
|
fc97ef6a24
|
Added tests
|
1 year ago |
|
killian
|
d2496fa8a2
|
Removed print statements, better audio playback
|
1 year ago |
|
killian
|
4640b4f1a0
|
Use official OI server. 3 second latency.
|
1 year ago |
|
killian
|
fef311e5b3
|
Updated realtimestt, removed print statements
|
1 year ago |
|
killian
|
6ee37e7f66
|
Updated packages, only run `mpv` if needed
|
1 year ago |
|
killian
|
296d84ebd2
|
Global interpreter
|
1 year ago |
|
killian
|
d8d7658f8a
|
Restored sending TTS service to client
|
1 year ago |
|
killian
|
d13c0cf3a4
|
Open Interpreter compatible `--profiles`
|
1 year ago |
|
killian
|
fda23e95b2
|
Implemented `profiles`
|
1 year ago |
