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

+20 -1
View File
@@ -61,6 +61,11 @@ import {
phoneRotationSetting,
ringConnectionModeSetting,
sonioxApiKeySetting,
saveTranscribeAudioSetting,
whisperServerApiKeySetting,
whisperServerLanguageSetting,
whisperServerModelSetting,
whisperServerUrlSetting,
screenFadeSetting,
enumSettingMenuItem,
firmwareDebugFlagsSetting,
@@ -124,6 +129,7 @@ function settingsSections(): SettingsSection[] {
items: [
enumSettingMenuItem(wakeWordActionSetting),
enumSettingMenuItem(voiceProviderSetting),
...whisperServerMenuItems(),
asrModelMenuItem("moonshine"),
asrModelMenuItem("whisper-base-en"),
],
@@ -237,7 +243,7 @@ function settingsSections(): SettingsSection[] {
if (section.label === "Developer") return { ...section, items: [toggleSettingMenuItem(showBleBandwidthSetting)] };
// No downloadable on-device models: iOS's on-device option is Apple's recognizer.
if (section.label === "Voice") return { label: "Voice", items: [enumSettingMenuItem(wakeWordActionSetting),
enumSettingMenuItem(voiceProviderSetting)] };
enumSettingMenuItem(voiceProviderSetting), toggleSettingMenuItem(saveTranscribeAudioSetting), ...whisperServerMenuItems()] };
if (deferred.has(section.label)) return { label: section.label, items: [{
label: "Not available on iOS yet", disabled: true, onSelect: () => {},
description: `${section.label} integration has not been ported to iOS.`,
@@ -451,6 +457,19 @@ function asrModelStatusText(id: AsrModelId): string {
return "not downloaded";
}
/**
* The self-hosted Whisper server's settings. Always listed: the provider
* option stays disabled until the URL is set.
*/
function whisperServerMenuItems(): MenuItem[] {
return [
textSettingMenuItem(whisperServerUrlSetting),
textSettingMenuItem(whisperServerModelSetting),
textSettingMenuItem(whisperServerLanguageSetting),
textSettingMenuItem(whisperServerApiKeySetting),
];
}
/** Download/cancel/delete management for one on-device transcription model. */
function asrModelMenuItem(id: AsrModelId): MenuItem {
const def = ASR_MODELS[id];