Skip to content

Add OpenAI cloud speech transcription#4707

Open
Jinwoo-H wants to merge 4 commits into
mainfrom
Jinwoo-H/feature-voice-speech-to-text-using-cloud-llm-mod
Open

Add OpenAI cloud speech transcription#4707
Jinwoo-H wants to merge 4 commits into
mainfrom
Jinwoo-H/feature-voice-speech-to-text-using-cloud-llm-mod

Conversation

@Jinwoo-H
Copy link
Copy Markdown
Contributor

@Jinwoo-H Jinwoo-H commented Jun 5, 2026

Summary

  • add OpenAI GPT-4o transcription model options to Voice settings
  • store the OpenAI speech API key locally with Electron safeStorage when available
  • route OpenAI speech dictation through the cloud transcription client and sanitize provider errors before showing toasts
  • keep OpenAI key configuration progressively disclosed under the Speech Model setting

Closes #4634

Testing

  • pnpm exec vitest run --config config/vitest.config.ts src/main/speech/model-manager.test.ts src/main/speech/stt-service.test.ts src/main/speech/openai-transcription-client.test.ts src/main/ipc/speech.test.ts src/renderer/src/components/settings/VoicePane.test.tsx
  • pnpm exec oxlint src/main/ipc/speech.ts src/main/ipc/speech.test.ts src/main/speech/model-catalog.ts src/main/speech/model-manager.ts src/main/speech/model-manager.test.ts src/main/speech/stt-service.ts src/main/speech/stt-service.test.ts src/main/speech/openai-api-key-store.ts src/main/speech/openai-transcription-client.ts src/main/speech/openai-transcription-client.test.ts src/preload/api-types.ts src/preload/index.ts src/renderer/src/components/dictation/DictationController.tsx src/renderer/src/components/settings/VoicePane.tsx src/renderer/src/components/settings/VoicePane.test.tsx src/renderer/src/components/settings/OpenAiTranscriptionKeyDialog.tsx src/renderer/src/components/settings/OpenAiTranscriptionSettingsRow.tsx src/renderer/src/components/settings/voice-dictation-toggle.ts src/renderer/src/components/settings/voice-pane-search.ts src/shared/constants.ts src/shared/speech-types.ts
  • pnpm run typecheck:node
  • pnpm run typecheck:web
  • git diff --check

Made with Orca 🐋

Jinwoo-H and others added 4 commits June 5, 2026 10:49
Co-authored-by: Orca <help@stably.ai>
Co-authored-by: Orca <help@stably.ai>
Co-authored-by: Orca <help@stably.ai>
Co-authored-by: Orca <help@stably.ai>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[Feature]: Voice speech to text using cloud LLM models (not Whisper)

1 participant