Aleix Conchillo Flaqué
159e403ae4
MoondreamService: yield vision response and text frames
2025-12-17 10:42:08 -08:00
Aleix Conchillo Flaqué
d3d50ac580
frames: added vision response and text frames
2025-12-17 10:42:08 -08:00
Aleix Conchillo Flaqué
d07b37b288
scripts(evals): more eval prompts improvements
2025-12-17 09:55:12 -08:00
Mark Backman
ca97d9dc4b
Merge pull request #3249 from pipecat-ai/mb/cleanup-pipecat-version
...
Clean up use of pipecat version
2025-12-17 12:17:53 -05:00
Mark Backman
6d84f36d05
Merge pull request #3214 from pipecat-ai/mb/update-run-inference
...
Update run_inference to use the provided LLM configuration params
2025-12-17 12:03:50 -05:00
Paul Kompfner
cdd6f5aa6a
Fix Anthropic LLM's run_inference so that it works even when extended thinking is enabled
2025-12-17 11:55:46 -05:00
Mark Backman
f1a0d547ce
Clean up use of pipecat version
2025-12-17 11:49:54 -05:00
mattie ruth backman
b1b7fc6357
Bump the RTVI version to 1.1.0 and add pipecat versioning to the botReady about field
2025-12-17 11:48:02 -05:00
Mark Backman
16e304016d
SimpleTextAggregator: Strip whitespace in the returned aggregation
2025-12-17 11:33:39 -05:00
Mark Backman
21a55f6aae
Update run_inference to use the provided LLM configuration params
2025-12-17 10:58:05 -05:00
Mark Backman
c8a86059fb
Merge pull request #3245 from simopot/add-soniox-language-hints-strict
...
Add language_hints_strict parameter to SonioxSTTService
2025-12-17 08:43:25 -05:00
Mark Backman
c537d7bafb
Merge pull request #3235 from pipecat-ai/mb/dev-runner-daily-pstn-dialin
...
Added Daily PSTN dial-in support to the development runner
2025-12-17 08:31:42 -05:00
Simo Potinkara
1fce68cef1
Add language_hints_strict parameter to SonioxSTTService
...
Add support for the language_hints_strict parameter in Soniox STT
configuration. When set to true, this parameter strictly enforces
language hints, restricting transcription to only the specified
languages.
2025-12-17 13:24:26 +02:00
Aleix Conchillo Flaqué
db983cb693
BaseObject: log file and line number for uncaught exceptions
2025-12-16 17:29:14 -08:00
Aleix Conchillo Flaqué
ac7b06faba
WordTTSService: make sure word timestamps are always started
2025-12-16 14:00:52 -08:00
Mark Backman
afa7573834
Merge pull request #3239 from pipecat-ai/mb/update-inworld-tts
...
Inworld TTS services: Add websocket TTS class, add word-timestamp ali…
2025-12-16 16:26:43 -05:00
kompfner
9e49e09360
Merge pull request #3226 from pipecat-ai/filipi/elevenlabs_http_voice_settings
...
Fixed an issue where ElevenLabsHttpTTSService was not updating voice settings
2025-12-16 16:07:34 -05:00
kompfner
b5221cd2c1
Merge pull request #3234 from hwuiwon/hw/bugfix-llmcontext
...
Fix LLM context tool audio content handling
2025-12-16 16:04:16 -05:00
Hwuiwon Kim
796f3aeff3
fix
2025-12-16 15:56:08 -05:00
Mark Backman
de94790b94
Merge pull request #3236 from pipecat-ai/mb/websocket-stt-services
...
Update websocket STT services to use the WebsocketSTTService base class
2025-12-16 13:59:52 -05:00
Mark Backman
bd3bf9a00e
Inworld TTS services: Add websocket TTS class, add word-timestamp alignment
2025-12-16 13:47:24 -05:00
kompfner
92f934031d
Merge pull request #3224 from pipecat-ai/pk/simplify-gemini-thinking
...
Clean up logic related to applying Gemini thought signatures to conte…
2025-12-16 13:35:17 -05:00
Mark Backman
11b92d89d0
Add session ID to GladiaSTTService logs, reset bytes_sent counter
2025-12-16 10:06:16 -05:00
Mark Backman
24b5efb9d8
Update SonioxSTTService to use WebsocketSTTService
2025-12-16 09:46:35 -05:00
Mark Backman
eeb3b85e39
Update AWSTranscribeSTTService to use WebsocketSTTService
2025-12-16 09:37:31 -05:00
Mark Backman
8255770b6c
Update AssemblyAISTTService to use WebsocketSTTService
2025-12-16 09:30:03 -05:00
Mark Backman
d3f918eb58
Update GladiaSTTService to use WebsocketSTTService
2025-12-16 09:20:53 -05:00
Mark Backman
36c6549426
Added Daily PSTN dial-in support to the development runner
2025-12-15 19:10:00 -05:00
Aleix Conchillo Flaqué
88d909d468
Merge pull request #3231 from pipecat-ai/aleix/improve-evals-assert-on-exit
...
evals: use EndFrame reason field to provide eval result
2025-12-15 13:23:29 -08:00
Hwuiwon Kim
27647fc067
Fix LLM context tool conversion and audio content handling
2025-12-15 13:43:57 -05:00
Paul Kompfner
54926f390d
Make image writing to and reading from LLMContext more robust; let's allow storing in context image types other than JPEG, meaning not lossily and unnecessarily re-encoding non-JPEG images as JPEG.
2025-12-15 10:39:36 -05:00
Kingston Kuan
50362ca37e
Merge branch 'pipecat-ai:main' into fix/smallwebrtcrequesthandler-return-type
2025-12-15 16:41:59 +08:00
Aleix Conchillo Flaqué
a5e42337a4
frames: EndFrame and CancelFrame reason is now Any
2025-12-14 12:16:14 -08:00
Aleix Conchillo Flaqué
4f848e9631
Merge pull request #3227 from fixie-ai/mike/upstream
...
Add Ultravox service
2025-12-13 18:29:02 -08:00
Kingston
93df7044fa
fix return type for SmallWebRTCRequestHandler
2025-12-13 22:11:06 +08:00
Paul Kompfner
e604e9b490
Support conversations with Gemini 3 Pro Image (model "gemini-3-pro-image-preview").
...
Prior to this change, after the model generated an image the conversation would not be able to progress. It would stall out because we were never storing the image in context, so the model would never realize it already did the work of generating an image. We didn't run into issues with Gemini 2.5 Flash Image, because that model always followed up an image with a text message.
2025-12-12 18:20:17 -05:00
Mike Depinet
2e4fa3f8db
PR comments
...
Also satisfy some Pyright complaints and update default model
2025-12-12 15:03:31 -08:00
Mark Backman
6cda357ce8
Remove timestamp check from TestThoughtTranscription
2025-12-12 14:28:39 -05:00
Mark Backman
7e87f61d17
Update GeminiLiveLLMService model to gemini-2.5-flash-native-audio-preview-12-2025
2025-12-12 14:18:57 -05:00
Mike Depinet
4b81be7acf
Add Ultravox service ( #1 )
...
Adds support for using Ultravox Realtime as a speech-to-speech service.
Also removes the deprecated Ultravox speech-to-text vllm model integration to avoid confusion.
2025-12-12 10:16:15 -08:00
Paul Kompfner
abc2ad8cbc
Avoid printing out entire thought signatures in logs
2025-12-12 13:01:45 -05:00
Paul Kompfner
64471d65f8
Clean up logic related to applying Gemini thought signatures to context messages
2025-12-12 12:53:11 -05:00
Filipi Fuchter
71d6516a14
Fixed an issue where ElevenLabsHttpTTSService was not updating voice settings when receiving a TTSUpdateSettingsFrame.
2025-12-12 14:46:24 -03:00
Filipi Fuchter
b25ad21941
Refactoring HeyGenVideoService and HeyGenTransport to work with both APIs.
2025-12-12 08:51:35 -03:00
Filipi Fuchter
c2abe42a64
Adding support for the HeyGen LiveAvatar API.
2025-12-12 08:49:52 -03:00
Filipi Fuchter
56dee06a29
Refactored the Interactive Avatar API to extend the HeyGen base API.
2025-12-12 08:49:16 -03:00
Filipi Fuchter
60cc14cafd
Created HeyGen base API to support both Interactive Avatar and LiveAvatar.
2025-12-12 08:48:39 -03:00
kompfner
1e98094394
Merge pull request #3175 from pipecat-ai/pk/thinking-exploration
...
Additional functionality related to thinking, for Google and Anthropic LLMs.
2025-12-11 17:15:37 -05:00
Paul Kompfner
0e88ad672e
Add ThoughtTranscriptionMessage.role, which is always "assistant"
2025-12-11 14:41:16 -05:00
kompfner
f41c3dcbc3
Merge pull request #3212 from pipecat-ai/pk/nova-2-sonic
...
Nova 2 Sonic support
2025-12-11 09:36:50 -05:00
