Skip to content

feat: single daemon with local OpenAI-compatible STT service#245

Draft
krystophny wants to merge 1 commit intomainfrom
feature/single-daemon-openai-stt-api
Draft

feat: single daemon with local OpenAI-compatible STT service#245
krystophny wants to merge 1 commit intomainfrom
feature/single-daemon-openai-stt-api

Conversation

@krystophny
Copy link
Collaborator

@krystophny krystophny commented Mar 1, 2026

Summary

  • add in-process HTTP service with OpenAI-compatible endpoints (/v1/audio/transcriptions, /v1/audio/translations, /healthz)
  • run service alongside the daemon hotkey loop in the same process
  • add service config + CLI/env overrides for bind host/port, request timeout, upload limits, and allowed languages
  • add request-level language/prompt overrides in whisper transcriber via transcribe_with_options
  • add end-to-end tests that use existing RemoteTranscriber client against the new local service

Design notes

  • no auth in voxtype service (loopback-first)
  • service defaults to constrained language set (de, en) when request language is not pinned
  • WAV decode/downmix/resample to 16k mono is handled server-side

Testing

  • cargo test

Closes #244

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: single daemon for hotkey dictation + OpenAI-compatible local STT API

1 participant