Mark Backman
e159f2dce1
Merge pull request #1024 from pipecat-ai/mb/elevenlabs-http
...
Add ElevenLabsHttpTTSService
2025-01-17 21:30:31 -05:00
Aleix Conchillo Flaqué
e9162ae467
Merge pull request #1004 from Fluentsai/feature/dtmf_input
...
Twilio serializer reading dtmf websocket messages
2025-01-17 18:14:46 -08:00
Aleix Conchillo Flaqué
bb65512ff4
Merge pull request #1034 from pipecat-ai/aleix/ulaw-resample-update
...
ulaw resample update
2025-01-17 17:47:18 -08:00
Mark Backman
b81323d676
Code review fixes + docstrings
2025-01-17 20:12:43 -05:00
Aleix Conchillo Flaqué
65fa77dfa5
audio: use resample_audio to resample ulaw bytes
2025-01-17 15:24:41 -08:00
Aleix Conchillo Flaqué
9ddd9ae27c
Merge pull request #1011 from Vaibhav159/vl_deepgram_metrics_without_vad
...
adding metric generation without deepgram VAD
2025-01-17 14:47:19 -08:00
Aleix Conchillo Flaqué
12fc6e17ef
Merge pull request #1033 from pipecat-ai/aleix/observers-performance
...
task: add TaskObserver and avoid pipeline blocking
2025-01-17 14:43:26 -08:00
Aleix Conchillo Flaqué
3e4020cdba
task: add TaskObserver and avoid pipeline blocking
...
Observers now process frames in separate tasks. This avoids blocking the
pipeline while the observer is processing the frame.
2025-01-17 11:15:52 -08:00
Aleix Conchillo Flaqué
4f883ee31f
Merge pull request #1023 from pipecat-ai/aleix/introduce-heartbeat-frames
...
introduce heartbeat frames
2025-01-17 10:31:07 -08:00
Mark Backman
3ff360f042
Merge pull request #1032 from pipecat-ai/mb/user-idle-fixes
...
Start UserIdleProcessor on speaking frame, fix bug not pushing EndFrame
2025-01-17 13:18:09 -05:00
Aleix Conchillo Flaqué
45cbad5b3e
task: add HEARTBEAT_MONITOR_SECONDS
2025-01-17 10:11:28 -08:00
Aleix Conchillo Flaqué
477d0d154b
frame_processor: make sure clock is initialized
2025-01-17 10:05:23 -08:00
Aleix Conchillo Flaqué
4b3c776f58
task: don't use push queue to send a heartbeat
...
This is because we might be waiting for the EndFrame. Currently, if we push an
EndFrame to the task, the task will block until the EndFrame traverses all the
pipeline.
2025-01-17 10:04:24 -08:00
Aleix Conchillo Flaqué
da0c4cfd99
task: increase heartbeat monitoring to 5 seconds
2025-01-17 10:04:05 -08:00
Aleix Conchillo Flaqué
f22a00570d
task: start heartbeats task when push task starts
2025-01-17 10:03:13 -08:00
Mark Backman
85f4663a41
Start UserIdleProcessor on speaking frame, fix bug not pushing EndFrame
2025-01-17 12:54:17 -05:00
Aleix Conchillo Flaqué
915e3bb3c7
Merge pull request #1029 from Vaibhav159/vl_fixing_idle_frame_processor_logic
...
fixing IdleFrameProcessor and UserIdleProcessor init logic
2025-01-17 06:48:13 -08:00
Vaibhav159
80779c48d6
sort fix
2025-01-17 20:07:25 +05:30
Vaibhav159
c444557965
fixing IdleFrameProcessor and UserIdleProcessor init logic
2025-01-17 19:50:53 +05:30
Mark Backman
d51893f61c
Refactor for aiohttp, correct use of settings
2025-01-16 23:49:53 -05:00
Mark Backman
740d2743df
Add TTFB metrics
2025-01-16 23:05:53 -05:00
Mark Backman
0dd22fb879
Merge pull request #1022 from pipecat-ai/mb/fix-abstractmethod
...
Remove @abstractmethod from set_model and set_model in TTSService class
2025-01-16 22:59:26 -05:00
Mark Backman
225b65c3d2
Add ElevenLabsHttpTTSService
2025-01-16 22:46:32 -05:00
Aleix Conchillo Flaqué
2503f76107
examples: add 31-heartbeats.py
2025-01-16 19:31:13 -08:00
Aleix Conchillo Flaqué
ff8aa68942
introduce heartbeat frames
2025-01-16 19:31:13 -08:00
Maxim Makatchev
c5edbf4b75
Made InputDTMFFrame a DataFrame and moved up to data frames
2025-01-17 12:27:04 +09:00
Aleix Conchillo Flaqué
799777774b
Merge pull request #1018 from pipecat-ai/aleix/streamline-thread-pool-executors
...
transports: streamline max_workers for ThreadPoolExecutors
2025-01-16 19:05:41 -08:00
Mark Backman
fdef8a97e2
Remove @abstractmethod from set_model and set_model in TTSService class
2025-01-16 21:36:51 -05:00
Mark Backman
0163247410
Merge pull request #1021 from pipecat-ai/mb/improve-30
...
Add a second observer to the 30-observer.py example
2025-01-16 21:19:35 -05:00
James Hush
221e044046
demo: Update translator bot example ( #1005 )
...
* docs: Update translator bot example
Updates the translator bot to do the following:
- Allow you to specify the in and out languages
- Uses TranscriptionProcessor to handle transcriptions
* Simplify the example, improve performance
---------
Co-authored-by: Mark Backman <mark@daily.co >
2025-01-17 10:08:15 +08:00
Mark Backman
532fd31fd7
Add a second observer to the 30-observer.py example
2025-01-16 19:46:18 -05:00
Mark Backman
3e178fd46f
Merge pull request #1020 from pipecat-ai/mb/observer-foundational
...
Add foundational example 30 to show how to use an Observer
2025-01-16 19:28:26 -05:00
Mark Backman
07cb8b7a89
Extend the example to include BotStartedSpeakingFrame and BotStoppedSpeakingFrame
2025-01-16 19:24:01 -05:00
Mark Backman
e805738d4c
Merge pull request #1009 from pipecat-ai/mb/tts-ignore-interim-transcripts
...
TTSService should only process LLMTextFrames
2025-01-16 17:09:24 -05:00
Mark Backman
119bc7e35f
Update check to exclude transcription frames
2025-01-16 16:43:46 -05:00
Mark Backman
b9b02845a3
Add foundational example 30 to show how to use an Observer
2025-01-16 16:37:32 -05:00
Aleix Conchillo Flaqué
3714f12edc
Merge pull request #1019 from Canonical-AI-Inc/canonical-transcripts
...
Add transcript to Canonical Metrics Service
2025-01-16 13:36:55 -08:00
Aleix Conchillo Flaqué
d2b8171197
transports: streamline max_workers for ThreadPoolExecutors
2025-01-16 13:34:04 -08:00
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
73ed0c1ad7
Merge pull request #1017 from pipecat-ai/aleix/additional-trace-logging
...
additional trace logging
2025-01-16 12:38:47 -08:00
Vanessa Pyne
c211580fec
Merge pull request #1016 from pipecat-ai/vp-1007-nonetype
...
services(gemini_multimodal_live): set content to [] if not present in messages
2025-01-16 14:14:50 -06:00
Aleix Conchillo Flaqué
359b55a85e
additional trace logging
2025-01-16 11:19:42 -08:00
kompfner
8b602a3f62
Merge pull request #1010 from pipecat-ai/ios-simplechatbot-assorted-improvements
...
iOS SimpleChatbot assorted improvements
2025-01-16 13:59:45 -05:00
kompfner
485c231f69
Merge pull request #1012 from pipecat-ai/simplechatbot-readme-local-pipecat
...
Add to the SimpleChatbot server README a step for pointing to the loc…
2025-01-16 13:46:19 -05:00
vipyne
8ba3b150eb
services(gemini_multimodal_live): set content to [] if not present in messages
...
... which it will be if the message is a tool call
2025-01-16 11:59:02 -06:00
Paul Kompfner
b5f72b4378
Add to the SimpleChatbot server README a step for pointing to the local version of pipecat
2025-01-16 11:59:44 -05:00
Vaibhav159
85e7d62f94
fixing log text
2025-01-16 21:36:51 +05:30
Vaibhav159
923d33eeff
fixing ruff
2025-01-16 21:32:48 +05:30
Vaibhav159
7ee6e7193d
adding metric generation without deepgram VAD
2025-01-16 21:23:56 +05:30
Paul Kompfner
156fffe6fc
In iOS SimpleChatbot demo, add clarifying note to Audio Settings section header explaining that "(No selection = system default)".
...
Ideally we could add a row showing that the system default is selected, but this is OK as a short-term fix. Also, the presence of that row might suggest that "system default" is selectable, but it's not: this is currently a limitation in the Pipecat Client.
2025-01-16 10:32:55 -05:00
