- "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>
23 lines
842 B
TypeScript
23 lines
842 B
TypeScript
/** The 44-byte header of a 16 kHz mono PCM16 WAV file holding `dataBytes` of samples. */
|
|
export function wavHeader(dataBytes: number): Uint8Array {
|
|
const header = new Uint8Array(44);
|
|
const view = new DataView(header.buffer);
|
|
const ascii = (offset: number, text: string) => {
|
|
for (let i = 0; i < text.length; i++) header[offset + i] = text.charCodeAt(i);
|
|
};
|
|
ascii(0, "RIFF");
|
|
view.setUint32(4, 36 + dataBytes, true);
|
|
ascii(8, "WAVE");
|
|
ascii(12, "fmt ");
|
|
view.setUint32(16, 16, true);
|
|
view.setUint16(20, 1, true); // PCM
|
|
view.setUint16(22, 1, true); // mono
|
|
view.setUint32(24, 16000, true);
|
|
view.setUint32(28, 32000, true); // byte rate
|
|
view.setUint16(32, 2, true); // block align
|
|
view.setUint16(34, 16, true); // bits per sample
|
|
ascii(36, "data");
|
|
view.setUint32(40, dataBytes, true);
|
|
return header;
|
|
}
|