Voice: self-hosted Whisper server provider; Transcribe on iOS

- "Whisper server (self-hosted)" transcription provider for OpenAI-compatible
  Whisper servers (vLLM, speaches, LocalAI) over plain HTTP batch requests,
  with URL, model, language and key settings (Voice). Pause-ended spans are
  one request each, finalized in audio order, with provisional text while a
  span is open. See notes/whisper-server.md.
- Transcribe (and other continuous capture) works on iOS with a cloud or
  Whisper-server provider; push-to-talk shares a running capture.
- Transcribe saves each session's audio as transcribe-<time>.wav in Downloads
  (setting "Save Transcribe audio", on by default), written as it is captured
  so a crash leaves a playable file; a saved transcript uses the same stamp.
- Calculator stops continuous listening when its window closes.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
FilipAlexanderandClaude Opus 5.5 committed 2026-10-17 16:43:18 +02:00
1 parent ecb6c7f465
commit e2caf28392
24 files changed
+1065 -43

No files matched your search

+3 -1
View File
@@ -6,7 +6,9 @@ const ts = require('typescript');
const path = require('node:path');
// The provider settings ios-preview-controller hands the voice bridge.
const voiceSettings = { voiceProviderSetting: { get: () => 'onboard' }, elevenLabsApiKeySetting: { get: () => '' },
openAiApiKeySetting: { get: () => '' }, sonioxApiKeySetting: { get: () => '' } };
openAiApiKeySetting: { get: () => '' }, sonioxApiKeySetting: { get: () => '' },
whisperServerUrlSetting: { get: () => '' }, whisperServerModelSetting: { get: () => '' },
whisperServerLanguageSetting: { get: () => '' }, whisperServerApiKeySetting: { get: () => '' } };
function load(file, context) {
const sandbox = { exports: {}, ...context };
const source = fs.readFileSync(path.join(__dirname, '..', file), 'utf8');