Add crunch presets, echo options, and streaming word mode

This commit is contained in:
Fisto
2026-09-21 12:31:43 +02:00
parent bbb580deea
commit c66d00ee59
11 changed files with 371 additions and 17 deletions
+35 -3
View File
@@ -6,6 +6,7 @@
* them in the transcript, and runs speech to text when a provider is set.
*/
import { statSync } from "node:fs";
import { AudioManager } from "./audio.js";
import type { CaptureSegment } from "./capture.js";
import { CapturePipeline } from "./capture.js";
@@ -146,6 +147,19 @@ export class AudioService {
return { queued: true, id, position: this.queue.length };
}
/** Wait for the wrapper's streaming file to appear, then play it while it grows. */
private async playWhenReady(file: string): Promise<void> {
for (let attempt = 0; attempt < 400; attempt++) {
try {
if (statSync(file).size > 44) break;
} catch {
// not created yet
}
await new Promise(resolve => setTimeout(resolve, 25));
}
await this.manager.play(file);
}
stop(): void {
this.queue.length = 0;
this.manager.stopPlayback();
@@ -350,9 +364,27 @@ export class AudioService {
this.playing = true;
try {
const file = await this.tts.synthesize(item.text, item.options);
await this.applyDuck(this.shouldDuck());
await this.manager.play(file);
// Streaming word mode: the wrapper writes the WAV while it synthesizes, so
// playback starts on the first word instead of after the whole line.
let streaming: Promise<void> | null = null;
const options: TtsOptions = { ...item.options };
if (item.options.stream === true) {
options.onOutputPath = path => {
streaming = (async () => {
await this.applyDuck(this.shouldDuck());
await this.playWhenReady(path);
})();
};
}
const file = await this.tts.synthesize(item.text, options);
const pending: Promise<void> | null = streaming;
if (pending) {
await pending;
} else {
await this.applyDuck(this.shouldDuck());
await this.manager.play(file);
}
} catch (error) {
console.error("[audio] speak failed:", (error as Error).message);
} finally {