Kwindla Hultman Kramer
|
5426891feb
|
added input audio pause setting. no frame to update that state, yet.
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
1c5ccd3406
|
fixes for settings updates, context updates, and response creation
|
2024-10-12 21:58:11 -07:00 |
|
Mark Backman
|
3a745bfa3f
|
Handle self._context of None
|
2024-10-12 21:58:11 -07:00 |
|
Mark Backman
|
ac4e39991e
|
Update ai_services for OpenAI Realtime param inputs
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
c870832da6
|
types seem complete; some ws error handling
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
e782016c57
|
renamed a file
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
00badaf98e
|
more pydantic cleanup
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
7dfac0163b
|
bits of pydantic
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
09a3c2a82d
|
major functionality working (not configurable, occasional timing bugs maybe)
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
c32c65014b
|
definitely broke something in the pipeline
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
f082eb10a2
|
small cleanup
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
b8898e449e
|
lots of debugging statements. multiple function calls broken
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
4fa0318005
|
configurability via constructor
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
93ebb9d541
|
working 19-openai-realtime-beta.py example
|
2024-10-12 21:58:11 -07:00 |
|
Kwindla Hultman Kramer
|
16101c79c5
|
beginning of realtime impl
|
2024-10-12 21:58:11 -07:00 |
|
Mark Backman
|
cbecae40a9
|
Mark the Markdown processor a util, and allow it to take inputs
|
2024-10-10 16:43:48 -04:00 |
|
Mark Backman
|
5b8753c8b6
|
Add speak_code input param
|
2024-10-10 13:17:37 -04:00 |
|
Mark Backman
|
3c5f9457f1
|
More edge case improvements
|
2024-10-10 12:07:00 -04:00 |
|
Mark Backman
|
788aec665b
|
Add a new processor which removes markdown and special chars from TTS text
|
2024-10-10 07:11:31 -04:00 |
|
Mark Backman
|
e21fb520f9
|
Make bot-tts-text messages urgent
|
2024-10-08 17:07:08 -04:00 |
|
Aleix Conchillo Flaqué
|
8cdb9ab1ad
|
rtvi: internal transport message should be urgent
|
2024-10-07 08:04:14 -07:00 |
|
Mark Backman
|
5dbf26d283
|
Handle cases where text is either a list or a string
|
2024-10-07 07:21:32 -04:00 |
|
Mark Backman
|
8001bab9b0
|
Remove another instance of urgent=true
|
2024-10-07 06:58:32 -04:00 |
|
Aleix Conchillo Flaqué
|
12d0686adc
|
rtvi: rename bot-audio to bot-tts-audio
|
2024-10-06 16:50:55 -07:00 |
|
Aleix Conchillo Flaqué
|
a28a5e954a
|
add TransportMessageSystemFrame
|
2024-10-06 16:50:12 -07:00 |
|
Aleix Conchillo Flaqué
|
bb966a89d2
|
rtvi: add RTVIUserLLMTextProcessor
|
2024-10-06 01:05:58 -07:00 |
|
Aleix Conchillo Flaqué
|
4a74eb3321
|
use isinstance tuples
|
2024-10-06 00:45:27 -07:00 |
|
Mark Backman
|
7796a272ce
|
Improve language handling for TTS services
|
2024-10-03 23:09:27 -04:00 |
|
Mark Backman
|
45c7d36b2e
|
Deepgram: disconnect and reconnect on language change
|
2024-10-03 12:31:42 -04:00 |
|
Aleix Conchillo Flaqué
|
65eeb0f1f6
|
Merge pull request #540 from pipecat-ai/cb/interruption-fix
Fixed RTVI `tts:interrupt` action not interrupting
|
2024-10-02 13:46:52 -07:00 |
|
Aleix Conchillo Flaqué
|
598936bc53
|
services: apply service language code before using service
|
2024-10-02 13:30:01 -07:00 |
|
Chad Bailey
|
b1bf6f7733
|
fixed botinterruptionframe
|
2024-10-02 19:43:51 +00:00 |
|
Aleix Conchillo Flaqué
|
0a37caf4b4
|
openai: fix image json logging
|
2024-10-02 11:57:50 -07:00 |
|
Aleix Conchillo Flaqué
|
6db65f4335
|
cartesia: use model_name instead of model_id
|
2024-10-02 11:57:36 -07:00 |
|
Aleix Conchillo Flaqué
|
3648874301
|
gladia: fix languages
|
2024-10-02 11:57:25 -07:00 |
|
Aleix Conchillo Flaqué
|
8bcb5d7fd2
|
services: async generators should yield frames
|
2024-10-02 11:57:08 -07:00 |
|
Aleix Conchillo Flaqué
|
8c01a900cd
|
google: allow using GOOGLE_APPLICATION_CREDENTIALS
|
2024-10-02 11:56:01 -07:00 |
|
Mark Backman
|
cd2e29f285
|
Fix nested strings issue
|
2024-10-02 12:26:30 -04:00 |
|
Mark Backman
|
3d642df2b0
|
Revert aligning voice_id name in TTS service constructor
|
2024-10-02 11:07:48 -04:00 |
|
Mark Backman
|
d75a02dc51
|
Use Language enum and set languages accordingly
|
2024-10-01 21:03:01 -04:00 |
|
Mark Backman
|
28643b453d
|
Update to use LLM, STT, TTS subclasses and remove setter methods
|
2024-10-01 20:30:27 -04:00 |
|
Mark Backman
|
88cca7bf68
|
Consolidate service UpdateSettingsFrame into a single ServiceUpdateSettingsFrame
|
2024-10-01 11:01:04 -04:00 |
|
Mark Backman
|
a397b859fe
|
Add support for gender and google_style inputs to Google TTS
|
2024-10-01 10:39:45 -04:00 |
|
Kwindla Hultman Kramer
|
8aae4e9856
|
Merge pull request #531 from pipecat-ai/khk/function-calling-improvements
|
2024-10-01 07:23:38 -07:00 |
|
Kwindla Hultman Kramer
|
92d8b37229
|
implement vision for openai
|
2024-09-30 21:49:29 -07:00 |
|
Kwindla Hultman Kramer
|
0801fc578b
|
Merge pull request #530 from pipecat-ai/khk/tts-say-fix
fix for multi-sentence tts say utterances
|
2024-09-30 20:59:53 -07:00 |
|
Kwindla Hultman Kramer
|
0d5cb84531
|
function calling testing and improvements
|
2024-09-30 20:59:28 -07:00 |
|
Kwindla Hultman Kramer
|
128355add5
|
fix for multi-sentence tts say utterances
|
2024-09-30 16:19:31 -07:00 |
|
Kwindla Hultman Kramer
|
0499fe41e4
|
get rid of some debug log lines used during development
|
2024-09-30 16:08:33 -07:00 |
|
Kwindla Hultman Kramer
|
6ad3437fd2
|
throw error if the llm tries to call a function that's not registered
|
2024-09-30 16:08:33 -07:00 |
|