v0.0.44
Added
-
Added support for OpenAI Realtime API with the new
OpenAILLMServiceRealtimeBeta
processor. (see https://platform.openai.com/docs/guides/realtime/overview) -
Added
RTVIBotTranscriptionProcessor
which will send the RTVIbot-transcription
protocol message. These are TTS text aggregated (into sentences) messages. -
Added new input params to the
MarkdownTextFilter
utility. You can setfilter_code
to filter code from text andfilter_tables
to filter tables from text. -
Added
CanonicalMetricsService
. This processor uses the newAudioBufferProcessor
to capture conversation audio and later send it to Canonical AI. (see https://canonical.chat/) -
Added
AudioBufferProcessor
. This processor can be used to buffer mixed user and bot audio. This can later be saved into an audio file or processed by some audio analyzer. -
Added
on_first_participant_joined
event toLiveKitTransport
.
Changed
-
LLM text responses are now logged properly as unicode characters.
-
UserStartedSpeakingFrame
,UserStoppedSpeakingFrame
,BotStartedSpeakingFrame
,BotStoppedSpeakingFrame
,BotSpeakingFrame
andUserImageRequestFrame
are now based fromSystemFrame
Fixed
-
Merge
RTVIBotLLMProcessor
/RTVIBotLLMTextProcessor
andRTVIBotTTSProcessor
/RTVIBotTTSTextProcessor
to avoid out of order issues. -
Fixed an issue in RTVI protocol that could cause a
bot-llm-stopped
orbot-tts-stopped
message to be sent before abot-llm-text
orbot-tts-text
message. -
Fixed
DeepgramSTTService
constructor settings not being merged with default ones. -
Fixed an issue in Daily transport that would cause tasks to be hanging if urgent transport messages were being sent from a transport event handler.
-
Fixed an issue in
BaseOutputTransport
that would causeEndFrame
to be pushed downed too early and callFrameProcessor.cleanup()
before letting the transport stop properly.