forked from Blendman974/faceclaw
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:
1 parent
ecb6c7f465
commit
e2caf28392
24 files changed
+1065
-43
No files matched your search
@@ -24,6 +24,8 @@ export class ReconnectingSttClient implements CloudSttClient {
|
||||
private readonly create: (options: CloudSttOptions) => CloudSttClient,
|
||||
private readonly options: CloudSttOptions,
|
||||
private readonly continuous: () => boolean,
|
||||
/** How long finish() waits for the provider's final transcript. */
|
||||
readonly finalTimeoutMs = 5000,
|
||||
) {}
|
||||
|
||||
start(): void {
|
||||
@@ -90,7 +92,7 @@ export class ReconnectingSttClient implements CloudSttClient {
|
||||
this.stop();
|
||||
return;
|
||||
}
|
||||
this.finishTimeout = setTimeout(() => this.stop(), 5000);
|
||||
this.finishTimeout = setTimeout(() => this.stop(), this.finalTimeoutMs);
|
||||
if (this.ready) this.client?.finish();
|
||||
}
|
||||
|
||||
|
||||
Reference in new issue
Block a user