Added
-
Added
audio_passthrough
parameter toSTTService
. If enabled it allows audio frames to be pushed downstream in case other processors need them. -
Added input parameter options for
PlayHTTTSService
andPlayHTHttpTTSService
.
Changed
-
Changed
DeepgramSTTService
model tonova-2-general
. -
Moved
SileroVAD
audio processor toprocessors.audio.vad
. -
Module
utils.audio
is nowaudio.utils
. A newresample_audio
function has been added. -
PlayHTTTSService
now uses PlayHT websockets instead of HTTP requests. -
The previous
PlayHTTTSService
HTTP implementation is nowPlayHTHttpTTSService
. -
PlayHTTTSService
andPlayHTHttpTTSService
now use avoice_engine
ofPlayHT3.0-mini
, which allows for multi-lingual support. -
Renamed
OpenAILLMServiceRealtimeBeta
toOpenAIRealtimeBetaLLMService
to match other services.
Deprecated
-
LLMUserResponseAggregator
andLLMAssistantResponseAggregator
are mostly deprecated, useOpenAILLMContext
instead. -
The
vad
package is now deprecated andaudio.vad
should be used instead. Theavd
package will get removed in a future release.
Fixed
-
Fixed an issue that would cause an error if no VAD analyzer was passed to
LiveKitTransport
params. -
Fixed
SileroVAD
processor to support interruptions properly.
Other
- Added
examples/foundational/07-interruptible-vad.py
. This is the same as07-interruptible.py
but using theSileroVAD
processor instead of passing theVADAnalyzer
in the transport.