dsh-ru-voice-input
Russian-first voice input bundle for DeepSeek Harness powered by local GigaAM v3 models.
Install
$ dsh plugin --profile web add https://github.com/tayuLuc/dsh-ru-voice-inputPlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Adds microphone voice input directly to the DeepSeek Harness composer
- Provides localized Russian speech recognition using local GigaAM v3 CTC/e2e models
- Supports multiple execution engines including MLX (Apple Silicon), onnx-asr, GGUF (transcribe-cpp), and ONNX int8
- Provides automated punctuation formatting via e2e models
- Includes customizable post-processing lexicon dictionary for terminology replacement
- Fixes standard speech-to-text registry bug to allow seamless language and provider switching
Useful For
- Dictating prompts and instructions in Russian directly into DeepSeek Harness
- Running local offline speech-to-text without sending audio data to external cloud APIs
- Technical dictation with custom glossary mappings for specialized jargon and abbreviations
Who It Fits
- Russian-speaking DeepSeek Harness users
- Developers needing local, private voice transcription on macOS, Linux, or Windows
- Users running DSH on Apple Silicon seeking hardware-accelerated MLX transcription
Documented Limitations
- Punctuation is only supported when running e2e engines (MLX or onnx-asr), not in base GGUF or ONNX int8 CTC engines
- Python 3.10+ and external dependencies (ffmpeg, venv packages) are required for MLX and onnx-asr sidecars
- Initial model downloads occur on first use and require disk space in ~/.dsh/models/
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
package.json declares 5 runtime, 0 development, 1 peer, and 0 optional dependencies.
package.json declares DSH bundle metadata.
GitHub reports the repository license as NOASSERTION.
A root package.json was captured and can be inspected by the registry.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- tayuLuc/dsh-ru-voice-input
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin Bundle
- Source checked
- 1bb17fb · 2026-09-27
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 0GitHub stars
- Forks
- 0
- Open issues
- 0
- Last commit
- 2026-09-27
- Last release
- No release detected
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Conversational data analysis agent for DSH that executes SQL, governs schema catalogs, and renders interactive reports.
View plugin →Multi-engine search provider for DeepSeek Harness with keyless fallback, time filtering, and UI configuration.
View plugin →Local-first AI agent runtime and DSH plugin bundle providing sandboxed sessions, MCP tools, audit logs, and session replay.
View plugin →Import and resume chat histories from 18+ AI coding agents into DeepSeek Harness with reverse export and sync.
View plugin →