Mark Backman
|
f2b07271c1
|
Update GroqLLMService to use llama-3.3-70b-versatile as the default model
|
2025-02-09 07:51:30 -05:00 |
|
Mark Backman
|
32b9de5f51
|
Add GroqSTTService, BaseWhisperSTTService, and refactor OpenAISTTService
|
2025-02-09 07:51:28 -05:00 |
|
Mark Backman
|
d67861925a
|
Merge pull request #1128 from golbin/whisper-api
Add Whisper STT service using OpenAI API
|
2025-02-08 08:35:26 -05:00 |
|
Mark Backman
|
0180619d44
|
Merge pull request #1173 from TheCodingLand/local-pyaudio-device-ids
adds configurable device ids for local audio transport
|
2025-02-08 08:04:00 -05:00 |
|
TheCodingLand
|
57964cb929
|
fix LocalAudioTransport param type
|
2025-02-08 12:32:20 +01:00 |
|
TheCodingLand
|
6840c77684
|
apply ruff formatting
|
2025-02-08 12:03:23 +01:00 |
|
Mark Backman
|
a1b58115ce
|
Deprecate stt_service parameter in STTMuteFilter
|
2025-02-07 19:24:03 -05:00 |
|
TheCodingLand
|
a359434307
|
remove Doc and Annotated imports
|
2025-02-07 19:42:34 +01:00 |
|
TheCodingLand
|
856c8959c3
|
enhance doc
|
2025-02-07 19:38:26 +01:00 |
|
TheCodingLand
|
8da7a42137
|
adds configurable input and output device ids for local audio
|
2025-02-07 19:23:18 +01:00 |
|
Aleix Conchillo Flaqué
|
510a0f5ef5
|
rtvi: deprecate RTVI.observer()
|
2025-02-07 09:19:43 -08:00 |
|
Aleix Conchillo Flaqué
|
03ac744bcf
|
rtvi: deprecate frame processors
|
2025-02-07 09:17:29 -08:00 |
|
Aleix Conchillo Flaqué
|
b058461a7d
|
GoogleRTVIObserver: add explicit constructor
|
2025-02-07 09:15:32 -08:00 |
|
Mark Backman
|
abd9f16b90
|
Export .rtvi, update new-chatbot example, rename and update foundational 32
|
2025-02-07 09:15:32 -08:00 |
|
Aleix Conchillo Flaqué
|
d07732f2e8
|
rtvi: separate specific google RTVI into a GoogleRTVIObserver
|
2025-02-07 09:15:32 -08:00 |
|
Aleix Conchillo Flaqué
|
070bf66980
|
transports: fix local transports audio cleanup
|
2025-02-06 13:45:13 -08:00 |
|
Aleix Conchillo Flaqué
|
a96d9294b7
|
tests: remove logger from tests.utils
|
2025-02-06 13:18:28 -08:00 |
|
Aleix Conchillo Flaqué
|
c4dbe92b30
|
prefer Optional over to "| None"
|
2025-02-06 11:11:37 -08:00 |
|
Aleix Conchillo Flaqué
|
c5d5ca8232
|
SentryMetrics: use transactions and call parent methods
|
2025-02-06 10:44:38 -08:00 |
|
Mark Backman
|
428e763814
|
Merge pull request #1149 from pipecat-ai/mb/update-google-default-llm-model
Use gemini-2.0-flash-001 as the default model for GoogleLLMService
|
2025-02-06 12:41:13 -05:00 |
|
Mark Backman
|
0efa2711ff
|
Merge pull request #1152 from pipecat-ai/mb/docstrings
Add docstrings for PipelineTask and related classes/functions
|
2025-02-06 12:30:12 -05:00 |
|
Mark Backman
|
4904f52cee
|
Use gemini-2.0-flash-001 as the default model for GoogleLLMService
|
2025-02-06 12:29:15 -05:00 |
|
Aleix Conchillo Flaqué
|
29b9dccc53
|
serializers: don't update twilio/telnyx sample rates
|
2025-02-06 09:25:52 -08:00 |
|
Aleix Conchillo Flaqué
|
e8ce826473
|
Merge pull request #1151 from pipecat-ai/aleix/base-output-transport-resample
BaseOutputTransport: resample incoming audio if needed
|
2025-02-06 09:25:07 -08:00 |
|
Mark Backman
|
4432e7e4f7
|
Add docstrings for PipelineTask and related classes/functions
|
2025-02-06 11:04:54 -05:00 |
|
Aleix Conchillo Flaqué
|
ee9cce64b2
|
BaseInputTransport: show VAD results when interruptions not allowed
|
2025-02-06 07:40:03 -08:00 |
|
Aleix Conchillo Flaqué
|
1ae4f0150d
|
BaseOutputTransport: resample incoming audio if needed
|
2025-02-06 07:37:43 -08:00 |
|
Mark Backman
|
4c77c3ed34
|
Merge pull request #1148 from pipecat-ai/mb/fix-twilio-serializer
Fix sample rate handling in Twilio and Telnyx serializers
|
2025-02-06 10:25:13 -05:00 |
|
Mark Backman
|
c8ccf13bc7
|
fix: Use audio_in_sample_rate to deserialize data for TelnyxFrameSerializer
|
2025-02-06 09:59:21 -05:00 |
|
Mark Backman
|
ba59736f87
|
fix: Use audio_in_sample_rate to deserialize data for TwilioFrameSerializer
|
2025-02-06 09:55:15 -05:00 |
|
Jin Kim
|
5989e1ed16
|
Merge branch 'main' into whisper-api
|
2025-02-06 13:14:36 +09:00 |
|
Aleix Conchillo Flaqué
|
bc21a0b817
|
FrameProcessor: add an error about missing super().process_frame(...)
|
2025-02-05 18:33:03 -08:00 |
|
Aleix Conchillo Flaqué
|
feab9c8fa2
|
tests: run_test() now uses PipelineTask
|
2025-02-05 10:34:38 -08:00 |
|
Aleix Conchillo Flaqué
|
61f6669926
|
task: allow passing StartFrame metadata via start_metadata param
|
2025-02-05 10:34:38 -08:00 |
|
Aleix Conchillo Flaqué
|
3be69908d2
|
Merge pull request #1131 from pipecat-ai/aleix/global-audio-sample-rates
introduce PipelineParams audio input/output sample rates
|
2025-02-05 08:11:25 -08:00 |
|
Aleix Conchillo Flaqué
|
fcb80ec330
|
playht: don't set sample_rate in _settings
|
2025-02-05 07:46:24 -08:00 |
|
Mark Backman
|
c9f5684e2f
|
OpenAITTSService: Add warning about changing sample_rate
|
2025-02-05 10:13:46 -05:00 |
|
Mark Backman
|
c257fa1573
|
AzureTTSService, AzureHttpTTSService: add start() method
|
2025-02-05 10:05:19 -05:00 |
|
Mark Backman
|
97c55da29f
|
PlayHTHttpTTSService: add start() method to set sample_rate
|
2025-02-05 09:54:41 -05:00 |
|
Aleix Conchillo Flaqué
|
49426aa9a1
|
transport(websocket): improve exception logging
|
2025-02-04 23:50:45 -08:00 |
|
Aleix Conchillo Flaqué
|
0a333c26da
|
services(elevenlabs): warn if sample rate not supported
|
2025-02-04 23:50:21 -08:00 |
|
Filipi Fuchter
|
7f1ae4b8cc
|
Fixing the issue in Krisp when trying to create more than one filter in the same process.
|
2025-02-04 20:10:56 -03:00 |
|
Aleix Conchillo Flaqué
|
ab45e481be
|
introduce PipelineParams audio input/output sample rates
|
2025-02-04 14:12:56 -08:00 |
|
Pedro Moreira
|
79ac696973
|
Add support for Piper TTS
|
2025-02-04 13:51:33 -03:00 |
|
Jin Kim
|
3cb189eb1f
|
Add whisper STT service using OpenAI API
|
2025-02-04 10:27:28 +09:00 |
|
Aleix Conchillo Flaqué
|
57dadb6359
|
audio(utils): some variable renames
|
2025-02-03 09:33:04 -08:00 |
|
Aleix Conchillo Flaqué
|
aafb2db620
|
GatedOpenAILLMContextAggregator: use keyword argument and add start_open
|
2025-02-03 09:16:44 -08:00 |
|
Aleix Conchillo Flaqué
|
f3f22cf61c
|
AudioBufferProcessor: add start_recording()/stop_recording()
|
2025-02-01 11:06:58 -08:00 |
|
Aleix Conchillo Flaqué
|
371c2f3704
|
canonical: do not reset audio buffers
|
2025-02-01 11:06:58 -08:00 |
|
Aleix Conchillo Flaqué
|
1f14f62696
|
AudioBufferProcessor: fix audio buffer silence computation
|
2025-02-01 11:06:58 -08:00 |
|