Pete
258e83c904
Fix: Correct Gemini Live API text input to prevent 1007 WebSocket errors
...
- Restore TextInputMessage.realtimeInput structure for correct API format
- Remove invalid turnComplete message from _send_user_text method
- turnComplete is only valid for clientContent, not realtimeInput messages
- realtimeInput text completion is automatically inferred by the API
This fixes WebSocket 1007 errors caused by mixing realtimeInput and
clientContent message types in violation of the Gemini Live API contract.
2025-08-03 10:58:59 -04:00
Pete
cccd82a617
Refactor TextInputMessage class to replace realtimeInput with a text attribute.
...
This was sending a 1007 because it was wrapping RealtimeInput in the json.
- Updated the `TextInputMessage` class to directly store text input as a string.
- Modified the `from_text` class method to create an instance using the new `text` attribute.
2025-08-02 14:34:00 -04:00
Pete
2af3b6329d
Ruff format debug
2025-07-29 17:48:11 -04:00
Pete
8ca06e5887
Add InputTextRawFrame class for handling raw text input in frames
...
- Introduced `InputTextRawFrame` to represent raw text input from users or programs.
- Updated `GeminiMultimodalLiveLLMService` to process `InputTextRawFrame` and send user text via the Gemini Live API's realtime input stream.
- Enhanced `_send_user_text` method documentation for clarity on its functionality and usage.
2025-07-29 17:43:14 -04:00
Pete
8f74b97591
Refactor _send_user_text method in Gemini multimodal service to streamline event creation for turn completion
2025-07-20 18:08:45 -04:00
Pete
1d69cd1a5e
Remove debug logging from _send_user_text method in Gemini multimodal service
2025-07-20 18:04:57 -04:00
Pete
bd7a0f27cc
Add text input handling to Gemini multimodal service
...
- Updated `RealtimeInput` to include an optional `text` parameter.
- Introduced `TextInputMessage` class for encapsulating text input data.
- Implemented `_send_user_text` method to send text input to the Gemini Live API.
- Enhanced message processing to support text input alongside media chunks.
2025-07-20 17:39:31 -04:00
kompfner
d4e33663b2
Merge pull request #2214 from pipecat-ai/pk/fix-google-llm-context
...
Fixed an issue in `GoogleLLMContext` where it would inject the `syste…
2025-07-18 09:28:28 -04:00
marcus-daily
d7d1b16dad
Removing old import
2025-07-18 12:48:06 +01:00
marcus-daily
0bc2ea13f2
Updating changelog
2025-07-18 12:48:06 +01:00
marcus-daily
b5d1301221
Fix linter warnings
2025-07-18 12:48:06 +01:00
marcus-daily
ed8f30ec71
Add support for running smart-turn-v2 locally
2025-07-18 12:48:06 +01:00
kompfner
a74a935ca0
Merge pull request #1910 from matejmarinko-soniox/main
...
Add Soniox STT service integration
2025-07-17 09:29:07 -04:00
Paul Kompfner
7cfd56699b
Fixed an issue in GoogleLLMContext where it would inject the system_message as a "user" message into cases where it was not meant to; it was only meant to do that when there were no "regular" (non-function-call) messages in the context, to ensure that inference would run properly.
2025-07-16 16:07:53 -04:00
Matej Marinko
cb984237a7
Fix lint error
2025-07-16 16:54:28 +02:00
Matej Marinko
c969fdddb9
Rename and simplify VAD finalization parameter usage
2025-07-16 09:47:34 +02:00
Mark Backman
9931ad2ce1
Merge pull request #2199 from Dev-Khant/add-host-support-in-Mem0
...
Add `host` support in Mem0 Memory
2025-07-15 11:41:15 -07:00
Filipi da Silva Fuchter
fd73feb645
Merge pull request #2201 from pipecat-ai/filipi/stt_issue
...
Only create the EmulateUserStartedSpeakingFrame if we have received a transcription
2025-07-15 13:56:11 -03:00
Filipi Fuchter
727af2e6fb
Only create the EmulateUserStartedSpeakingFrame if we have received a transcription.
2025-07-14 17:38:03 -03:00
Mark Backman
8fd5576879
Merge pull request #2198 from Allenmylath/patch-24
...
Update app.py
2025-07-14 06:37:42 -07:00
kompfner
1f85dcee7c
Merge pull request #2171 from pipecat-ai/pk/aws-strands-demo
...
Minimal AWS Strands demo
2025-07-14 09:32:16 -04:00
Dev Khant
138890bc5c
Add support in Mem0 Memory
2025-07-14 18:08:25 +05:30
Filipi da Silva Fuchter
a094efc9e6
Merge pull request #2196 from pipecat-ai/mb/lmnt-model
...
LmntTTSService: update the default model to blizzard
2025-07-14 09:15:17 -03:00
allenmylath
1f9e2fdecc
Update app.py
...
misleading comment. no endpoints.py
2025-07-14 14:02:35 +05:30
Mark Backman
4a2b4660bc
LmntTTSService: update the default model to blizzard
2025-07-13 10:54:43 -07:00
Mark Backman
b3ac90015a
Merge pull request #2195 from Trinary-Projects/transformers_ver_patch
...
Update transformers dep. to >=4.48.0 for Ultravox
2025-07-11 23:31:47 -07:00
Jaideep
2fe06f0a4e
Update pyproject.toml
2025-07-12 11:34:45 +05:30
Mark Backman
1836a7484e
Merge pull request #2193 from pipecat-ai/mb/changelog-0.0.76
...
Prepare changelog for 0.0.76 release
2025-07-11 16:15:34 -07:00
Mark Backman
25a5c5aaab
Prepare changelog for 0.0.76 release
2025-07-11 16:08:08 -07:00
mattie ruth backman
24694e2558
Changelog entry
2025-07-11 14:30:12 -07:00
mattie ruth backman
2325edd9ba
Add a text entry box to the simple-chatbot example
2025-07-11 14:30:12 -07:00
mattie ruth backman
fad5713ade
Fix append-to-context function call
2025-07-11 14:30:12 -07:00
Paul Kompfner
fe8573322f
AWS Strands demos
2025-07-11 16:42:27 -04:00
Mark Backman
06c1255abe
fix: use a different aggregation timeout for emulated user speech ( #2185 )
...
* fix: use a different aggregation timeout for emulated user speech
* Add SpeechControlParamsFrame
* Update test_context_aggregator tests
2025-07-11 16:33:44 -04:00
Mark Backman
f108a67635
Merge pull request #2189 from pipecat-ai/mb/numpy-version-bump
...
Update numpy, transformers to support newer versions
2025-07-11 12:02:02 -07:00
Mark Backman
bf580d061d
Update numpy, transformers to support newer versions
2025-07-11 11:58:31 -07:00
Filipi da Silva Fuchter
b005bd7b98
Merge pull request #2184 from pipecat-ai/filipi/twilio_issue
...
Fixing an issue where Pipecat was not receiving the user's audio
2025-07-11 15:32:28 -03:00
Filipi Fuchter
75f8baab33
Mentioning the fixes in the changelog.
2025-07-11 11:56:16 -03:00
Matej Marinko
5c3fb73cef
Rename example
2025-07-11 16:07:24 +02:00
Filipi Fuchter
5c3f4180b9
Refactored VAD analyzer to process multiple audio frames in a single iteration if needed.
2025-07-11 10:59:32 -03:00
Mark Backman
6cd6e7ceed
Merge pull request #2186 from pipecat-ai/mb/fix-pre-commit-config
...
Update .pre-commit-config.yaml to use pyproject.toml linting rules
2025-07-11 06:34:01 -07:00
Filipi Fuchter
1a146c2a64
Not serializing a JSON in case we have no audio.
2025-07-11 10:15:09 -03:00
Filipi Fuchter
eaeb9e6efa
Not creating InputAudioRawFrame in case we don't have bytes. Fixed for Pilvo, Exotel and Telnyx.
2025-07-11 09:51:38 -03:00
Matej Marinko
2e84c91748
Remove outdated parameter
2025-07-11 08:52:39 +02:00
Matej Marinko
650d45c1f4
Use single sample rate parameter
2025-07-11 08:27:06 +02:00
Filipi Fuchter
f4f65024ef
Refactoring the test client to use the new version of the Pipecat Client SDK.
2025-07-10 21:57:25 -03:00
Filipi Fuchter
1200aa4fb8
Not creating InputAudioRawFrame in case we don't have bytes.
2025-07-10 21:56:34 -03:00
Filipi da Silva Fuchter
6762363685
Merge pull request #2183 from pipecat-ai/filipi/parallel_pipeline_issue
...
Fixed an issue in ParallelPipeline that caused errors when attempting to drain the queues.
2025-07-10 21:51:04 -03:00
Filipi Fuchter
b2ead325c4
Fixed an issue in ParallelPipeline that caused errors when attempting to drain the queues.
2025-07-10 21:50:35 -03:00
Mark Backman
4e24b915cc
Update .pre-commit-config.yaml to use pyproject.toml linting rules
2025-07-10 16:10:27 -07:00
