Vaibhav159
f37626f81d
adding more daily room params
2025-01-07 21:38:05 +05:30
Mark Backman
12b5c5a646
Fix truncation timing of OpenAIRealtimeBetaLLMService
2025-01-06 15:37:58 -05:00
Mark Backman
3e1ec4a8ee
Added support for Google Journey TTS voices
2025-01-06 14:54:34 -05:00
Mark Backman
a1377b7f1a
Merge pull request #924 from xtreme-sameer-vohra/patch-1
...
Update frames.py
2025-01-06 14:13:10 -05:00
Mark Backman
4667624b60
Update copyright to 2025
2025-01-06 10:19:37 -05:00
Sameer Vohra
d07ba80572
Update frames.py
...
fix minor typo in docs
2025-01-05 22:57:54 -05:00
Kwindla Hultman Kramer
ab3bcde5f7
Merge pull request #907 from pipecat-ai/khk/gemini-20241221
...
Gemini unary API fixes and natural conversation demo
2024-12-23 17:34:57 -08:00
Kwindla Hultman Kramer
a5e985094b
remove stray line
2024-12-22 19:45:57 -08:00
Aleix Conchillo Flaqué
c04c69df95
transports(base_output): fix duplicate push_frame()
2024-12-22 14:43:38 -08:00
Mark Backman
469c13c07e
Merge pull request #903 from pipecat-ai/mb/send-prebuilt-chat
...
Add the ability to send_prebuilt_chat_message when using the DailyTra…
2024-12-22 14:33:50 -05:00
Kwindla Hultman Kramer
ab5df1a236
feature complete gemini audio, transcription, and phrase endpointing demo
2024-12-22 11:19:02 -08:00
Kwindla Hultman Kramer
f5f0de00e4
still some cleanup to do
2024-12-21 23:04:00 -08:00
Kwindla Hultman Kramer
53a5e63990
function calling dead-end
2024-12-21 18:10:25 -08:00
Kwindla Hultman Kramer
59240c7b96
delay gemini multimodal live websocket connect
2024-12-21 14:36:37 -08:00
Mark Backman
6c11753985
Add the ability to send_prebuilt_chat_message when using the DailyTransport
2024-12-21 14:04:46 -05:00
Mark Backman
6fabb7e7d5
Fix metrics calculations
2024-12-21 13:25:43 -05:00
Mark Backman
627c91f4a6
Flush the audio
2024-12-21 12:52:28 -05:00
Mark Backman
dac4468ca1
Add Fish Audio TTS service
2024-12-21 12:42:56 -05:00
Mark Backman
503eddf7d6
Merge pull request #897 from pipecat-ai/mb/update-playht
...
Update PlayHT to use the latest Websocket connection endpoint
2024-12-20 20:31:41 -05:00
Aleix Conchillo Flaqué
1a0f6f2a21
Merge pull request #898 from pipecat-ai/aleix/reset-input-queue-flag-if-interruption
...
frame_processor: reset input queue flag with interruptions
2024-12-20 13:58:12 -08:00
Aleix Conchillo Flaqué
43759295cc
frame_processor: reset input queue flag with interruptions
2024-12-20 09:33:20 -08:00
Mark Backman
900b95eb92
Update PlayHT to use the latest Websocket connection endpoint
2024-12-20 10:44:47 -05:00
Mark Backman
9554804a49
Update 11L default model, allow language to be used by more models
2024-12-19 20:33:58 -05:00
Mark Backman
656cbc35e1
Make auto_mode an input parametere for ElevenLabsTTSService; add changelog entry
2024-12-19 20:33:56 -05:00
Aleix Conchillo Flaqué
8b496f8c6f
transports(daily): daily-python 0.14.0 (SIP transfer/refer, DTMF)
2024-12-19 17:08:29 -08:00
Aleix Conchillo Flaqué
15047f5f0a
Merge pull request #885 from pipecat-ai/aleix/parallelpipeline-wait-for-slowest-endframe
...
pipeline(parallel): wait for slowest endframe
2024-12-19 15:18:22 -08:00
Aleix Conchillo Flaqué
e08c24dc41
Merge pull request #883 from pipecat-ai/aleix/base-output-transport-avoid-pushing-endframe
...
transport(base output): avoid pushing EndFrame twice
2024-12-19 11:26:31 -08:00
Aleix Conchillo Flaqué
5341739ece
transport(base output): avoid pushing EndFrame twice
2024-12-19 11:19:49 -08:00
Louis Jordan
b7b8e59e9e
feat: set auto_mode=true - ElevenLabs tts WSS
2024-12-19 16:57:17 +00:00
Mark Backman
6e0d3aef32
Merge pull request #860 from pipecat-ai/mb/transcription
...
Add a TranscriptProcessor and new frames
2024-12-19 08:15:53 -05:00
Mark Backman
c9dd906057
Tailor chat completion inputs to Cerebras API
2024-12-19 08:10:33 -05:00
Mark Backman
4f093f11db
Add CerebrasLLMService and foundational example
2024-12-19 08:10:31 -05:00
Mark Backman
887a9170b2
Merge pull request #889 from pipecat-ai/mb/openai-realtime-model
...
Add model parameter to OpenAI realtime service constructor, update de…
2024-12-19 08:08:52 -05:00
Aleix Conchillo Flaqué
78b90e9591
Merge pull request #884 from pipecat-ai/aleix/filters-handle-endframe
...
processors(filters): allow passing EndFrame
2024-12-18 19:35:56 -08:00
Aleix Conchillo Flaqué
17decee788
Merge pull request #882 from pipecat-ai/aleix/stop-transport-parent-first
...
transports: call parent stop() before disconnecting
2024-12-18 19:35:39 -08:00
Mark Backman
3b3e22fe7c
Add model parameter to OpenAI realtime service constructor, update default model
2024-12-18 18:12:51 -05:00
Mark Backman
8a7a61914e
Code review feedback
2024-12-17 22:35:13 -05:00
Mark Backman
1117c21483
Refactor TranscriptProcessor into user and assistant processors
2024-12-17 22:34:22 -05:00
Mark Backman
4211664a77
TranscriptProcessor to handle simple and list content
2024-12-17 22:34:03 -05:00
Mark Backman
1f8a217cd1
Code review changes
2024-12-17 22:34:02 -05:00
Mark Backman
dd2703317a
Add timestamp frames and include timestamps in the transcription event and frame
2024-12-17 22:31:15 -05:00
Mark Backman
77aeda36eb
Update OpenAI's from_standard_message to convert back to OpenAI's simple format
2024-12-17 22:31:15 -05:00
Mark Backman
51b235df4b
Add docstrings for Google and Anthropic's to_standard_messages and from_standard_message functions
2024-12-17 22:31:15 -05:00
Mark Backman
4f2aee5fba
Update OpenAI's to_standard_messages to return the verboase message format
2024-12-17 22:31:15 -05:00
Mark Backman
55879bf365
Add TranscriptionProcessor
2024-12-17 22:31:15 -05:00
Aleix Conchillo Flaqué
7322badbe7
audio(koala): add new audio filter KoalaFilter
2024-12-17 18:45:10 -08:00
Aleix Conchillo Flaqué
42bea578e8
pipeline(parallel): wait for slowest endframe
...
If we are sending an EndFrame and a ParallelPipeline has multiple pipelines we
want to wait before pushing the EndFrame downstream until the slowest pipeline
is finished. Otherwise, we could be disconnecting from the transport too early.
2024-12-17 17:05:11 -08:00
Aleix Conchillo Flaqué
2dfdceb9e6
processors(filters): allow passing EndFrame
2024-12-17 16:22:19 -08:00
Aleix Conchillo Flaqué
5bfcac1f5c
transports: call parent stop() before disconnecting
...
This rollbacks a previous change https://github.com/pipecat-ai/pipecat/pull/855
which was trying to fix an issue in the wrong way.
The reasoning behind this fix is that the parent class might be sending audio or
messages (through the subclass) and if we disconnect before all the data is sent
we will run into incomplete audio or even errors. Therefore, we first make sure
the parent tasks stop and then it will be safe to disconnect.
2024-12-17 16:02:33 -08:00
Aleix Conchillo Flaqué
17162258a2
fix ruff linter import organization
2024-12-17 11:28:58 -08:00
