Skip to main content
Version: 2026.07.0

Speech to Text Changelog

2.2.0 (2026-06-29)​

Updated​

  • [PLAT-1551] Updated ONNX Runtime to 1.24.4 using CUDA 13 in GPU docker image

Added​

  • [VOX-3310] Support for LM-X floating and node-locked license files (hidden behind a feature flag)
  • [PLAT-1538] technology_name field to phonexia.grpc.common.Status/GetStatus gRPC method response
  • [PLAT-1544] Docker healthcheck using grpc-health-probe for container orchestration

Fixed​

  • [PLAT-1538] Remove unused secure option from phonexia.grpc.common.Status/GetStatus gRPC method

2.1.1 (2026-01-13)​

  • Fixed license validation error handling for legacy (v1) license files with missing required fields. Previously, this could cause undefined behavior.

2.1.0 (2025-12-08)​

Added​

  • [PLAT-1403] Richer error model (see Error handling for more details)

Changed​

  • [PLAT-1471] Refactoring of the internal audio handling to reduce memory usage. Audio format support is now limited to WAV and FLAC.

Fixed​

  • [PLAT-1509] Fixed GPU processing failure on NVIDIA Blackwell architecture GPUs (e.g., RTX 1000 series) caused by a bug in ONNX Runtime.

2.0.0 (2025-11-25)​

Breaking change​

  • [PLAT-1425] Improve compatibility with future models - WARNING microservice requires latest models

Changed​

  • Microservice now by default logs each request with incremental correlation id

Fixed​

  • [PLAT-1442] Context cancellation validation
  • [VOX-2666] Inconsistent logging
  • [PLAT-1277] Possible memory leak on cuda device

1.0.0 (2025-07-07)​

Added​

  • Speech to text microservice