Whisper Local for DeepSeek Harness

Local, offline speech recognition for the DeepSeek Harness Web GUI, powered by whisper.cpp. It plugs into the Harness voice-input pipeline as a host-local speech provider: audio is recorded by the browser, transcribed on the Host machine, and never sent over the network.

• No OpenAI account, no API key.
• 99 Whisper languages plus automatic language detection.
• Model selector built into the Harness UI.
• Managed runtime and model downloads with size + SHA-256 verification.
• Agent tool whisper_model so the assistant can inspect and change the model.

This is a community bundle, not an official DeepSeek plugin.

Table of contents

• Features
• How it works
• Requirements
• Installation
• Usage
• Models
• Configuration
• Agent tool
• Data and privacy
• Troubleshooting
• Development
• Limitations
• Acknowledgements

Features

• Fully local dictation | whisper-cli.exe runs on the CPU; the model and audio stay on the machine.
• Automatic language detection by default | language: auto lets Whisper identify each recording's language; any of the 99 Whisper languages can still be forced from the voice settings.
• Model selection in the UI | pick tiny, base, small, medium or large-v3-turbo from the plugin page; the change is persisted and applied immediately.
• Managed setup | the Windows x64 whisper.cpp runtime and GGML model are downloaded on demand, verified (size + SHA-256), cached, and reused offline.
• No microphone data retention | each recording is written to a temporary WAV, transcribed, then deleted.
• Agent integration | the assistant can list models, download one in the background, or switch the active model through whisper_model.

How it works

Browser (Harness composer)
  └─ microphone button records 16 kHz mono PCM WAV
       └─ speech Remote sends the recording to the Host
            └─ whisper-local SpeechProvider
                 ├─ writes a temporary WAV
                 ├─ spawns whisper-cli.exe with the selected GGML model
                 ├─ reads the text output
                 └─ deletes the temporary files and returns the transcript

The provider registers through ctx.speechToText.register() and advertises itself as location: 'host-local', so the voice UI shows preparation state and lets the user download the model when needed.

Requirements

Requirement	Details
DeepSeek Harness	Desktop/Web build with the experimental Voice Input bundle enabled
OS	Windows 10/11 x64 (the pinned runtime is a Windows CPU build)
Runtime	tar.exe (built into Windows 10/11) for extracting the runtime archive
Disk	~90 MB for the extracted runtime + 31–547 MB per model (see table)
CPU	Any x64 CPU; more cores and threads improve speed. GPU is not used
Microphone	OS + browser microphone permission

No Node.js, Python, compiler, or CUDA installation is required at runtime.

Installation

From GitHub (recommended)

1. Enable the official Voice Input bundle: Plugins → Voice Input.

2. Open Plugins → Add plugin → Install a third-party plugin.

3. Enter the repository Git address:

   git+https://github.com/Linj1k/dsh-whisper-local.git
   

   Pin a release for reproducibility with git+https://github.com/Linj1k/dsh-whisper-local.git#v1.3.0.

4. Confirm the bundle is enabled. Its patch selects whisper-local with language: auto for the voice module and registers the whisper_model tool.

5. If the Host module was added while Harness is running and the provider does not appear, restart Harness once. Browser-only UI changes are hot-reloaded.

From a release tarball

Download dsh-whisper-local-1.3.0.tgz from the GitHub Releases page and point Plugins → Add plugin at the file.

From npm (after publication)

The package name is dsh-whisper-local. Once the maintainer has run npm publish, install it by entering the package name (optionally pinned, for example dsh-whisper-local@1.3.0) in Plugins → Add plugin.

From a local checkout

Install the absolute path of this folder through Plugins → Add plugin. Useful for development.

Usage

Dictation

1. Click the microphone button in the composer, between the model selector and Send.
2. Allow microphone access the first time.
3. Speak, then press Stop.
4. The transcript is inserted into the draft; review and send it normally.

Choosing a model

Open Plugins → Whisper local. The bundle page offers:

• a model dropdown with sizes and speed/accuracy hints;
• the currently active model;
• a Save model button.

The selection is written through the Harness Settings service into the profile configuration, so it survives restarts. If the chosen model is not downloaded yet, preparation starts automatically; progress is shown in the Voice Input bundle details (Download and prepare).

Language selection

Whisper local advertises 99 languages plus auto. Change the language in Plugins → Voice Input → bundle details → Language. The official selector displays translated labels for auto, en, zh, ja, ko; other languages appear as ISO codes such as fr, de, es, ja.

The default is auto (automatic detection), not a fixed language. French is not forced: a recording is detected on its own unless a specific language is selected. Automatic detection is a good default for mixed-language use; forcing the exact language improves reliability on short or noisy recordings.

Models

All models are multilingual Whisper GGML builds, hosted by ggerganov/whisper.cpp.

Key	File	Size (binary)	Notes
tiny-q5_1	ggml-tiny-q5_1.bin	~31 MB	Fastest, lowest accuracy
base-q5_1	ggml-base-q5_1.bin	~57 MB	Fast, basic accuracy
small-q5_1	ggml-small-q5_1.bin	~181 MB	Default; good balance
medium-q5_0	ggml-medium-q5_0.bin	~514 MB	More accurate, slower
large-v3-turbo-q5_0	ggml-large-v3-turbo-q5_0.bin	~547 MB	Best multilingual accuracy

Measured on an AMD Ryzen 9 9950X3D with 8 threads, for roughly 10 seconds of speech:

Model	French	Japanese
small-q5_1	~1.3 s	~1.2 s
large-v3-turbo-q5_0	~3.3 s	~4.0 s

The pinned whisper.cpp runtime is the official nightly b5454 Windows x64 OpenBLAS build, verified by its release SHA-256.

Configuration

The bundle patch (cordis.patch.yml) supplies defaults:

- insert:
    - id: whisper-local
      name: 'dsh-whisper-local'
      config:
        dataRoot: !!js dshHomePath('speech-to-text', 'whisper-local')
        model: small-q5_1
        threads: 8
        timeoutMs: 180000

- id: speech-to-text
  config:
    defaultProvider: whisper-local
    language: auto

Field	Default	Meaning
dataRoot	%USERPROFILE%\.dsh\speech-to-text\whisper-local	Managed location for runtime, models and diagnostics
model	small-q5_1	One of the model keys above; also editable from the UI
threads	8	CPU threads passed to whisper-cli
timeoutMs	180000	Per-transcription deadline
modelPath	unset	Use an existing GGML model file instead of a managed download
whisperCli	unset	Use an existing whisper-cli.exe instead of the managed runtime

User overrides are stored in the profile's patch layer and take precedence over the bundle defaults. The model selected from the UI is written there as well.

Agent tool

The bundle registers the whisper_model tool:

Action	Description
list	Model catalogue, downloaded state, active model, preparation phase, active downloads
download	Download a model in the background without changing the active model
set	Select a model and persist it through Settings; downloads it unless prepare=false
prepare	Prepare/download the currently selected model

Example: switch to the large model after downloading it in the background.

{ "action": "download", "model": "large-v3-turbo-q5_0" }
{ "action": "set", "model": "large-v3-turbo-q5_0", "prepare": false }

Data and privacy

• No network calls during dictation. The only network traffic is the one-time runtime/model download performed by the explicit preparation step.
• No API keys. The plugin never asks for or stores an OpenAI key.
• Temporary audio. Each recording becomes a temporary WAV under the OS temp directory and is removed in a finally block after transcription.
• Managed data lives in dataRoot:
  • runtime/ | extracted whisper.cpp build and runtime.json marker;
  • model/ | downloaded GGML models;
  • cache/ | downloaded runtime archive;
  • status.json | diagnostic snapshot (provider, model, languages, selected language, readiness). No audio or transcript content is stored there.
• Settings persistence uses the profile's cordis.patch.yml; the model choice contains no sensitive data.

Troubleshooting

The microphone says the provider is not ready. Open Plugins → Voice Input → details and use Download and prepare. The setup card downloads the runtime and model and shows progress.

The model selector shows "settings unavailable". The Harness Settings service or configForms client service is not mounted in this profile. Use the voice bundle's preparation page or edit model in the profile patch.

No audio is recognized. Check the OS microphone permission, that a model is prepared, and the selected language. Try auto, or force the spoken language. For quiet/short recordings, a larger model helps.

The plugin row is failed after an update. The bundled provider.js is plain JavaScript and needs no build, but Host modules are loaded once per process. Toggling the row or restarting Harness reloads the module. Check the row's diagnostic in Plugins.

Diagnostics. dataRoot/status.json reports the active model, advertised language count, selected provider/language and readiness. The agent can also call whisper_model with action: "list".

Development

No build step. The bundle is plain ESM/JavaScript.

File	Role
package.json	Bundle manifest (dsh.bundle.patch, dsh.client, exports)
cordis.patch.yml	Cordis rows: the provider and the voice selection override
index.js	Cordis entry; loads Schemastery from the dsh installation and declares the volatile model Config field
provider.js	Speech provider: preparation, downloads, verification, whisper-cli execution, whisper_model tool
client.js	Browser page: model selector through ctx.configForms
locale/*.json	Plugin-manager display metadata (en, fr, zh)
tests/*.mjs	Provider and client tests
tests/fixtures/*.wav	Small multilingual TTS fixtures for the integration tests

Tests

The provider tests run real transcription with the prepared model in the default dataRoot, so prepare the runtime/model first (or point WHISPER_LOCAL_DATA_ROOT at a prepared directory):

node tests/local-provider.test.mjs
node tests/client.test.mjs

The provider suite covers: provider registration and language list, idempotent preparation, real French transcription, unprepared-state errors, explicit English/German/Spanish/Japanese transcription, automatic detection, model listing through the agent tool, persistence through Settings and invalid model rejection.

Limitations

• Windows x64 only for the managed runtime. The provider logic is portable, but the pinned download is a Windows build; other platforms need a different whisperCli/runtime and extraction path.
• CPU inference only in this configuration; no GPU acceleration.
• Complete recordings only | no streaming captions, wake word or automatic send; those are capabilities of the voice subsystem, not this provider.
• Accuracy varies by model and language. Low-resource languages may need a larger model.
• The official Voice Input selector shows ISO codes for languages without a translated label.
• large-v3-turbo needs roughly 1–2 GB of RAM during inference and is slower than small; choose based on your hardware.

Publishing

npm login                 # once per machine
npm pack                  # produces dsh-whisper-local-1.3.0.tgz
git tag -a v1.3.0 -m "v1.3.0"
git push origin main --tags
npm publish --access public

The GitHub release can attach the tarball produced by npm pack. The npm name dsh-whisper-local is available and the package no longer sets private.

Acknowledgements

• whisper.cpp | MIT, runtime and GGML model format.
• OpenAI Whisper | model weights and language set.
• DeepSeek Harness | plugin, voice-input and settings APIs.

License

MIT. See LICENSE.