Basic Usage

Workspace

VoSonar opens to a workspace with these main entries:

  • Dictation
  • Media transcription
  • Live translation
  • Meeting transcription
  • History
  • Tools
  • Settings
  • Account

Dictation

Dictation records speech and injects recognized text into the target app.

  1. Focus the target text field.
  2. Click Start Dictation in VoSonar or press your saved hotkey.
  3. Speak normally.
  4. Stop recording and wait for recognition, post-processing, and injection.

The result appears in the injectable text area. You can copy it or retry injection if the target app rejects it.

Current post-processing includes whitespace cleanup, dictionary replacements, optional Chinese number normalization, and punctuation policy handling. It is not an unlimited rewrite engine.

Media Transcription

Media transcription imports local audio or video files and generates text you can save. Current capabilities include:

  • Local file transcription
  • Result display
  • TXT export
  • SRT export

Recognition quality depends on the packaged local ASR model, audio quality, and runtime environment.

Live Translation

The Live Translation page is wired for backend configuration, bilingual display, and TXT/Markdown export.

Supported configuration paths include:

  • Official Gateway cloud path
  • OpenAI-compatible providers
  • Ollama-compatible local providers

Cloud paths require sign-in, account entitlement, real provider configuration, and available quota. The app reports explicit errors for missing providers, quota exhaustion, expired sessions, or upstream failures.

Meeting Transcription

The Meeting page currently focuses on local single-speaker meeting capture and organization:

  • Start/stop meeting recording
  • Save meeting history
  • Review the transcript timeline
  • Generate AI summaries
  • Edit meeting note drafts
  • Export Markdown

Meeting capabilities that are not complete yet:

  • WebSocket multi-person collaboration
  • Real-time speaker diarization
  • Multi-speaker color labels
  • DOCX export and task-list closure

Tools and Settings

Tools includes dictionary rules, AI prompts, statistics, and legacy import status.

Settings includes recording, translation, privacy, subtitles, hotkeys, startup, and update options.

Account, Subscription, and Quota

The Account page lets you sign in and review plan, quota, and billing state. The website and member center now run in production, with account, subscription, usage, and payment entrypoints routed through Gateway. Payment channels, providers, backup/restore, download distribution, and desktop integration remain tracked through their own acceptance records.

If plan or quota state looks wrong, refresh account status first. If the problem remains, contact support with your account, timestamp, and error message.