NewYour coding agent can read the release notes before it upgrades.Set up the MCP server →
On-device speech recognition for Flutter powered by sherpa-onnx.
Last release 4 months ago
22 May 2026
Too new to tell
only 1 release windows
Most releases are documented
notes for 3 of 4 stable releases
Nothing withdrawn
no release was ever pulled
4 months old
4 releases · first in 2026
One column per month.
- bump version
Nothing published for this version
> Breaking change: This release removes all Android/Kotlin native code and
Breaking change: This release removes all Android/Kotlin native code and replaces the Platform Channel bridge with a pure-Dart implementation using the
sherpa_onnxFlutter package.
AsrLib now uses sherpa_onnx directly instead of
the previous Kotlin native AAR + Platform Channel bridge.sherpa_onnx + record).record package — replaces Android AudioRecord.asr_model_downloader.dart replaces the
Kotlin ModelDownloader. Supports progress tracking and marker-file-based
download state.silero_vad.onnx is now a Flutter asset.android/ directory removed — no native code needed.AsrConfig.modelType selects the model architecture:
zipformer_ctc (default), sense_voice, or paraformer.record, path_provider, path.plugin: declaration removed from pubspec.yaml.Android arm64-v8a support (minSdk 24).
Your coding agent can read these notes before it upgrades. Set up the MCP server →