Version: 2026.03.0-rc1 On this page
Phonexia Speaker Diarization
[PLAT-1506] Fixed a rare issue where audio resampling could fail when processing large files, particularly when converting between certain sample rates (e.g., 11025 Hz to 8000 Hz).
[PLAT-1509] Fixed GPU processing failure on NVIDIA Blackwell architecture GPUs (e.g., RTX 1000 series) caused by a bug in ONNX Runtime.
Fixed license validation error handling for legacy (v1) license files with missing required fields. Previously, this could cause undefined behavior.
[PLAT-1425] Improve compatibility with future models - WARNING microservice requires at least model v5.3.0
Microservice now by default logs each request with incremental correlation id
[VOX-2666] Inconsistent logging
[PLAT-1471] Refactoring of the internal audio handling to reduce memory usage. Audio format support is now limited to WAV and FLAC .
[PLAT-1277] Possible memory leak on cuda device
[PLAT-1430] Empty output on recording with long silence at the beginning
[PLAT-1056] Support for new licenses tied only to model major version. Old licenses tied to precise model version are still supported.
[PLAT-1070] Default port 8080 exposed in Dockerfile
[VOX-1293] phonexia.grpc.common.Status service
[VOX-1293] Field license_flags to LicensingInfoResult in phonexia.grpc.common.Licensing
[VOX-1497] Crash when recording sample rate is not divisible by 10 and processing start time has been set
[PLAT-978] Loading configuarion from model
[PLAT-967] Added PHX_NUM_THREADS_PER_INSTANCE, PHX_NUM_INSTANCES_PER_DEVICE and PHX_DEVICE_INDEX options for concurrent processing
[PLAT-389] Start and end request's messages are logged at the INFO level
[PLAT-936] Crash when using negative values in time range
[PLAT-888] Added PHX_KEEPALIVE_TIME_S and PHX_KEEPALIVE_TIMEOUT_S options for connection timeout specification
[PLAT-772] Support for sending RAW audio data
[PLAT-781] Support for license extensions
[PLAT-821] GPU enabled docker image for GPU acceleration of certain parts of the algorithm
[PLAT-758] Device is not logged by default
[PLAT-669] Add support for custom log tags in metadata and logs.
[PLAT-774] Optimized docker images.
[PLAT-464] Parameters for selecting the part of the audio to process in 'DiarizeRequest' ('audio.time_range')
[PLAT-520] Add support of correlation id for better tracking of requests
[PLAT-623] Processing cancellation when client closes the connection
[PLAT-625] Server configuration is logged at startup
[PLAT-532] Add config to request to specify the number of speakers and maximum number of speakers
[PLAT-614] Inconsistent license logging
Memory usage optimizations
[PLAT-340] New generation of speaker diarization