echogarden 3.2.0 → 3.4.0

package/dist/utilities/Timer.js

@@ -1,61 +1,73 @@
-import { logToStderr, roundToDigits } from './Utilities.js';
+import { logToStderr } from './Utilities.js';
 export class Timer {
+    logger;
     startTime = 0;
-    constructor() {
+    constructor(logger) {
+        if (logger) {
+            this.logger = logger;
+        }
+        else {
+            this.logger = logToStderr;
+        }
         this.restart();
     }
+    // Resets the timer to the current time.
     restart() {
         this.startTime = Timer.currentTime;
     }
+    // Elapsed time in milliseconds (monotonic where supported).
     get elapsedTime() {
-        // Elapsed time (milliseconds)
         return Timer.currentTime - this.startTime;
     }
+    // Elapsed time in seconds.
     get elapsedTimeSeconds() {
-        // Elapsed time (seconds)
         return this.elapsedTime / 1000;
     }
+    // Returns elapsed ms and restarts the timer.
     getElapsedTimeAndRestart() {
-        const elapsedTime = this.elapsedTime;
+        const elapsed = this.elapsedTime;
         this.restart();
-        return elapsedTime;
+        return elapsed;
     }
+    // Logs elapsed time (in ms) and restarts the timer.
     logAndRestart(title, timePrecision = 3) {
-        const elapsedTime = this.elapsedTime;
-        //
-        const message = `${title}: ${roundToDigits(elapsedTime, timePrecision)}ms`;
-        logToStderr(message);
-        //
+        const elapsedMs = this.elapsedTime;
+        this.logger(`${title}: ${roundToDigits(elapsedMs, timePrecision)}ms`);
         this.restart();
-        return elapsedTime;
+        return elapsedMs;
     }
+    // Current high-resolution timestamp in milliseconds since Unix epoch.
     static get currentTime() {
-        if (!this.getTimestamp) {
-            this.createTimestampFunction();
-        }
-        return this.getTimestamp();
+        return this.timestampFunc();
     }
+    // Current timestamp in microseconds (integer).
     static get microsecondTimestamp() {
         return Math.floor(Timer.currentTime * 1000);
     }
+    // Clock setup
+    static timestampFunc = Timer.createTimestampFunction();
     static createTimestampFunction() {
-        if (typeof process === 'object' && typeof process.hrtime === 'function') {
-            let baseTimestamp = 0;
-            this.getTimestamp = () => {
-                const nodeTimeNanoSeconds = process.hrtime.bigint();
-                const nodeTimeMilliseconds = Number(nodeTimeNanoSeconds) / 1_000_000;
-                return baseTimestamp + nodeTimeMilliseconds;
-            };
-            baseTimestamp = Date.now() - this.getTimestamp();
+        const g = globalThis;
+        // 1. Modern standard: performance.now() (Browsers & Node 16+)
+        if (typeof g.performance === 'object' && typeof g.performance.now === 'function') {
+            const timeOrigin = g.performance.timeOrigin ?? (Date.now() - g.performance.now());
+            return () => timeOrigin + g.performance.now();
         }
-        else if (typeof performance === 'object' && performance.now) {
-            const baseTimestamp = Date.now() - performance.now();
-            this.getTimestamp = () => baseTimestamp + performance.now();
+        // 2. Node.js high resolution timer (BigInt variant, Node 10.4+)
+        if (typeof g.process === 'object' && typeof g.process.hrtime === 'function') {
+            const startNs = g.process.hrtime.bigint();
+            const epochBaseMs = Date.now() - (Number(startNs) / 1e6);
+            return () => epochBaseMs + Number(g.process.hrtime.bigint()) / 1e6;
         }
-        else {
-            this.getTimestamp = () => Date.now();
+        // 3. Last-resort fallback (non-monotonic)
+        if (typeof Date.now === 'function') {
+            return () => Date.now();
         }
+        return () => new Date().getTime();
     }
-    static getTimestamp;
+}
+export function roundToDigits(value, digits) {
+    const factor = 10 ** digits;
+    return Math.round(value * factor) / factor;
 }
 //# sourceMappingURL=Timer.js.map

package/dist/utilities/Timer.js.map

@@ -1 +1 @@
-{"version":3,"file":"Timer.js","sourceRoot":"","sources":["../../src/utilities/Timer.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,aAAa,EAAE,MAAM,gBAAgB,CAAA;AAE3D,MAAM,OAAO,KAAK;IACjB,SAAS,GAAG,CAAC,CAAA;IAEb;QACC,IAAI,CAAC,OAAO,EAAE,CAAA;IACf,CAAC;IAED,OAAO;QACN,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,WAAW,CAAA;IACnC,CAAC;IAED,IAAI,WAAW;QACd,8BAA8B;QAC9B,OAAO,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,SAAS,CAAA;IAC1C,CAAC;IAED,IAAI,kBAAkB;QACrB,yBAAyB;QACzB,OAAO,IAAI,CAAC,WAAW,GAAG,IAAI,CAAA;IAC/B,CAAC;IAED,wBAAwB;QACvB,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,CAAA;QACpC,IAAI,CAAC,OAAO,EAAE,CAAA;QAEd,OAAO,WAAW,CAAA;IACnB,CAAC;IAED,aAAa,CAAC,KAAa,EAAE,aAAa,GAAG,CAAC;QAC7C,MAAM,WAAW,GAAG,IAAI,CAAC,WAAW,CAAA;QAEpC,EAAE;QACF,MAAM,OAAO,GAAG,GAAG,KAAK,KAAK,aAAa,CAAC,WAAW,EAAE,aAAa,CAAC,IAAI,CAAA;QAE1E,WAAW,CAAC,OAAO,CAAC,CAAA;QACpB,EAAE;QAEF,IAAI,CAAC,OAAO,EAAE,CAAA;QAEd,OAAO,WAAW,CAAA;IACnB,CAAC;IAED,MAAM,KAAK,WAAW;QACrB,IAAI,CAAC,IAAI,CAAC,YAAY,EAAE,CAAC;YACxB,IAAI,CAAC,uBAAuB,EAAE,CAAA;QAC/B,CAAC;QAED,OAAO,IAAI,CAAC,YAAY,EAAE,CAAA;IAC3B,CAAC;IAED,MAAM,KAAK,oBAAoB;QAC9B,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,CAAA;IAC5C,CAAC;IAEO,MAAM,CAAC,uBAAuB;QACrC,IAAI,OAAO,OAAO,KAAK,QAAQ,IAAI,OAAO,OAAO,CAAC,MAAM,KAAK,UAAU,EAAE,CAAC;YACzE,IAAI,aAAa,GAAG,CAAC,CAAA;YAErB,IAAI,CAAC,YAAY,GAAG,GAAG,EAAE;gBACxB,MAAM,mBAAmB,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,CAAA;gBACnD,MAAM,oBAAoB,GAAG,MAAM,CAAC,mBAAmB,CAAC,GAAG,SAAS,CAAA;gBAEpE,OAAO,aAAa,GAAG,oBAAoB,CAAA;YAC5C,CAAC,CAAA;YAED,aAAa,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,IAAI,CAAC,YAAY,EAAE,CAAA;QACjD,CAAC;aAAM,IAAI,OAAO,WAAW,KAAK,QAAQ,IAAI,WAAW,CAAC,GAAG,EAAE,CAAC;YAC/D,MAAM,aAAa,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;YAEpD,IAAI,CAAC,YAAY,GAAG,GAAG,EAAE,CAAC,aAAa,GAAG,WAAW,CAAC,GAAG,EAAE,CAAA;QAC5D,CAAC;aAAM,CAAC;YACP,IAAI,CAAC,YAAY,GAAG,GAAG,EAAE,CAAC,IAAI,CAAC,GAAG,EAAE,CAAA;QACrC,CAAC;IACF,CAAC;IAEO,MAAM,CAAC,YAAY,CAAc;CACzC"}
+{"version":3,"file":"Timer.js","sourceRoot":"","sources":["../../src/utilities/Timer.ts"],"names":[],"mappings":"AAAA,OAAO,EAAE,WAAW,EAAE,MAAM,gBAAgB,CAAA;AAE5C,MAAM,OAAO,KAAK;IACA,MAAM,CAAa;IAE5B,SAAS,GAAG,CAAC,CAAA;IAErB,YAAY,MAAoB;QAC/B,IAAI,MAAM,EAAE,CAAC;YACZ,IAAI,CAAC,MAAM,GAAG,MAAM,CAAA;QACrB,CAAC;aAAM,CAAC;YACP,IAAI,CAAC,MAAM,GAAG,WAAW,CAAA;QAC1B,CAAC;QAED,IAAI,CAAC,OAAO,EAAE,CAAA;IACf,CAAC;IAED,wCAAwC;IACxC,OAAO;QACN,IAAI,CAAC,SAAS,GAAG,KAAK,CAAC,WAAW,CAAA;IACnC,CAAC;IAED,4DAA4D;IAC5D,IAAI,WAAW;QACd,OAAO,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,SAAS,CAAA;IAC1C,CAAC;IAED,2BAA2B;IAC3B,IAAI,kBAAkB;QACrB,OAAO,IAAI,CAAC,WAAW,GAAG,IAAI,CAAA;IAC/B,CAAC;IAED,6CAA6C;IAC7C,wBAAwB;QACvB,MAAM,OAAO,GAAG,IAAI,CAAC,WAAW,CAAA;QAChC,IAAI,CAAC,OAAO,EAAE,CAAA;QAEd,OAAO,OAAO,CAAA;IACf,CAAC;IAED,oDAAoD;IACpD,aAAa,CAAC,KAAa,EAAE,aAAa,GAAG,CAAC;QAC7C,MAAM,SAAS,GAAG,IAAI,CAAC,WAAW,CAAA;QAClC,IAAI,CAAC,MAAM,CAAC,GAAG,KAAK,KAAK,aAAa,CAAC,SAAS,EAAE,aAAa,CAAC,IAAI,CAAC,CAAA;QACrE,IAAI,CAAC,OAAO,EAAE,CAAA;QAEd,OAAO,SAAS,CAAA;IACjB,CAAC;IAED,sEAAsE;IACtE,MAAM,KAAK,WAAW;QACrB,OAAO,IAAI,CAAC,aAAa,EAAE,CAAA;IAC5B,CAAC;IAED,+CAA+C;IAC/C,MAAM,KAAK,oBAAoB;QAC9B,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,CAAC,WAAW,GAAG,IAAI,CAAC,CAAA;IAC5C,CAAC;IAED,cAAc;IACN,MAAM,CAAC,aAAa,GAAiB,KAAK,CAAC,uBAAuB,EAAE,CAAA;IAEpE,MAAM,CAAC,uBAAuB;QACrC,MAAM,CAAC,GAAG,UAAiB,CAAA;QAE3B,8DAA8D;QAC9D,IAAI,OAAO,CAAC,CAAC,WAAW,KAAK,QAAQ,IAAI,OAAO,CAAC,CAAC,WAAW,CAAC,GAAG,KAAK,UAAU,EAAE,CAAC;YAClF,MAAM,UAAU,GACf,CAAC,CAAC,WAAW,CAAC,UAAU,IAAI,CAAC,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,CAAC,WAAW,CAAC,GAAG,EAAE,CAAC,CAAA;YAE/D,OAAO,GAAG,EAAE,CAAC,UAAU,GAAG,CAAC,CAAC,WAAW,CAAC,GAAG,EAAE,CAAA;QAC9C,CAAC;QAED,gEAAgE;QAChE,IAAI,OAAO,CAAC,CAAC,OAAO,KAAK,QAAQ,IAAI,OAAO,CAAC,CAAC,OAAO,CAAC,MAAM,KAAK,UAAU,EAAE,CAAC;YAC7E,MAAM,OAAO,GAAG,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,CAAA;YAEzC,MAAM,WAAW,GAAG,IAAI,CAAC,GAAG,EAAE,GAAG,CAAC,MAAM,CAAC,OAAO,CAAC,GAAG,GAAG,CAAC,CAAA;YAExD,OAAO,GAAG,EAAE,CACX,WAAW,GAAG,MAAM,CAAC,CAAC,CAAC,OAAO,CAAC,MAAM,CAAC,MAAM,EAAE,CAAC,GAAG,GAAG,CAAA;QACvD,CAAC;QAED,0CAA0C;QAC1C,IAAI,OAAO,IAAI,CAAC,GAAG,KAAK,UAAU,EAAE,CAAC;YACpC,OAAO,GAAG,EAAE,CAAC,IAAI,CAAC,GAAG,EAAE,CAAA;QACxB,CAAC;QAED,OAAO,GAAG,EAAE,CAAC,IAAI,IAAI,EAAE,CAAC,OAAO,EAAE,CAAA;IAClC,CAAC;CACD;AAED,MAAM,UAAU,aAAa,CAAC,KAAa,EAAE,MAAc;IAC1D,MAAM,MAAM,GAAG,EAAE,IAAI,MAAM,CAAA;IAE3B,OAAO,IAAI,CAAC,KAAK,CAAC,KAAK,GAAG,MAAM,CAAC,GAAG,MAAM,CAAA;AAC3C,CAAC"}

package/docs/API.md

@@ -3,14 +3,17 @@
 **Note**: the API is not fully stable yet. It may change at every new version. There are many methods, types and internal data structures that are not yet exposed.
 
 ### Importing as a Node.js module
+
 To import the `echograden` package as a Node.js module:
 
 Install as a dependency in your project:
+
 ```bash
 npm install echogarden
 ```
 
 Import with:
+
 ```ts
 import * as Echogarden from 'echogarden'
 ```
@@ -18,6 +21,7 @@ import * as Echogarden from 'echogarden'
 All methods, properties and arguments have TypeScript type information. You can use it to get more detailed and up-to-date type information that may not be covered here.
 
 ### Related pages
+
 * [Options reference](Options.md)
 * [List of all supported engines](Engines.md)
 * [Quick guide to the command line interface](CLI.md)
@@ -32,10 +36,10 @@ Synthesizes the given input.
 * `input`: text to synthesize, can be a `string`, or a `string[]`. When given an array of strings, the elements of the array would be seen as predefined segments (this is useful if you would like to have more control over how segments are split, or your input has a special format requiring a custom splitting method).
 * `options`: synthesis options object
 * `callbacks`: an object containing the optional properties:
-	* `onSegment`: a callback that is called whenever a segment has been synthesized
-	* `onSentence`: a callback that is called whenever a sentence has been synthesized
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `onSegment`: a callback that is called whenever a segment has been synthesized
+  * `onSentence`: a callback that is called whenever a sentence has been synthesized
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -48,13 +52,16 @@ Synthesizes the given input.
 ```
 
 `audio` may either be a
+
 * `RawAudio` object, which is a structure containing the sample rate and raw 32-bit float channels:
+
 ```ts
 {
 	sampleRate: number
 	channels: Float32Array[]
 }
 ```
+
 * A `Uint8Array` containing the audio in encoded form, in the case a particular codec was specified in the `outputAudioFormat.codec` option.
 
 #### Segment and sentence event callbacks
@@ -62,15 +69,19 @@ Synthesizes the given input.
 You can optionally pass two `async` callbacks to `synthesize`, `onSegment` and `onSentence`.
 
 For example:
+
 ```ts
 async function onSegment(data: SynthesisSegmentEventData) {
 	console.log(data.transcript)
 }
 
-const { audio } = await Echogarden.synthesize("Hello World!", { engine: 'espeak' }, onSegment)
+const { audio } = await Echogarden.synthesize('Hello World!', {
+	engine: 'espeak',
+}, onSegment)
 ```
 
 `SynthesisSegmentEventData` is an object with the structure:
+
 ```ts
 {
 	index: number              // Index of part
@@ -92,8 +103,8 @@ Requests a list of voices for a particular engine.
 
 * `options`: voice list request options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -113,8 +124,8 @@ Applies speech recognition to the input.
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: recognition options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -143,8 +154,8 @@ Aligns input audio with the given transcript.
 * `transcript`: the transcript to align to
 * `options`: alignment options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -171,10 +182,11 @@ Translates speech audio directly to a transcript in a different language (only E
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: speech translation options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	transcript: string
@@ -199,10 +211,11 @@ Translates text to text.
 * `input`: string
 * `options`: text translation options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	text: string
@@ -227,8 +240,8 @@ Aligns input audio with the given translated transcript.
 * `translatedTranscript`: the translated transcript to align to
 * `options`: translation alignment options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -256,8 +269,8 @@ Aligns input audio to both the native language transcript a translated one.
 * `translatedTranscript`: the translated transcript to align to
 * `options`: transcript and translation alignment options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -289,8 +302,8 @@ Aligns given timeline with its translated transcript.
 * `translatedTranscript`: the translated transcript to align to
 * `options`: timeline translation alignment options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
 
@@ -315,10 +328,11 @@ Detects language of spoken audio.
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: speech language detection options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	detectedLanguage: string
@@ -334,10 +348,11 @@ Detects language of text.
 * `input`: input text as `string`
 * `options`: text language detection options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	detectedLanguage: string
@@ -355,10 +370,11 @@ Detects voice activity in audio (non-real-time).
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: voice activity detection options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	timeline: Timeline
@@ -374,10 +390,11 @@ Tries to reduce background noise in spoken audio.
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: denoising options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	denoisedAudio: RawAudio
@@ -393,10 +410,11 @@ Attempts to isolate an individual [audio stem](https://en.wikipedia.org/wiki/Ste
 * `input`: can be an audio file path (`string`), encoded audio (`Buffer` or `Uint8array`) or a raw audio object (`RawAudio`)
 * `options`: source separation options object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns (via promise):
+
 ```ts
 {
 	inputRawAudio: RawAudio
@@ -414,8 +432,8 @@ Converts a timeline to subtitles.
 * `timeline`: timeline object
 * `options`: subtitles configuration object
 * `callbacks`: an object containing the optional properties:
-	* `abortSignal`: an abort signal (`AbortSignal`)
-	* `logLevel`: log level (`string`)
+  * `abortSignal`: an abort signal (`AbortSignal`)
+  * `logLevel`: log level (`string`)
 
 #### Returns:
 
@@ -441,7 +459,6 @@ Sets a global option.
 
 See the [options reference](Options.md) for more details about the available global options.
 
-
 ### `getGlobalOption(key)`
 
 Gets a global option.

package/docs/CLI.md

@@ -9,10 +9,12 @@ echogarden [operation] [one or more inputs..] [one or more outputs...] [options.
 Each operation can accept one or more options, in the form `--[optionName]=[value]` (The `=` is required).
 
 **Keyboard shortcuts**:
+
 * While the program is running, you can press `esc` to exit immediately
 * When audio is playing, you can press `enter` to skip it, `space` to pause/resume, `right` to skip 1 second forward, and `left` to skip 1 second backwards
 
 ### Related pages
+
 * [Options reference](Options.md)
 * [List of all supported engines](Engines.md)
 
@@ -21,41 +23,49 @@ Each operation can accept one or more options, in the form `--[optionName]=[valu
 **Task**: Given a text file, synthesize spoken audio for it.
 
 This would synthesize "Hello World" and play the result in the terminal:
+
 ```bash
 echogarden speak "Hello world!"
 ```
 
 If no language is specified, it would attempt to detect it. This usually works better for longer texts, and may misidentify shorter ones. To ensure the right language is selected, you can specify the language explicitly:
+
 ```bash
 echogarden speak "Hello world!" --language=en
 ```
 
 This would save the resulting audio to `result.mp3`:
+
 ```bash
 echogarden speak "Hello world!" result.mp3 --language=en
 ```
 
 `speak-file` synthesizes text loaded from a textual file, which can have the extensions `txt`, `html`, `xml`, `ssml`, `srt`, `vtt`:
+
 ```bash
 echogarden speak-file text.txt result.mp3 --language=en
 ```
 
 You can specify an engine using the `--engine` option (a full list of engines can be found [here](Engines.md)). This would set the synthesis engine to `pico` (SVOX Pico):
- ```bash
- echogarden speak-file text.txt result.mp3 --language=en --engine=pico
- ```
+
+```bash
+echogarden speak-file text.txt result.mp3 --language=en --engine=pico
+```
 
 The CLI supports multiple output files. This would synthesize a text file, and save the resulting audio in both `result.mp3` and `result.wav`, as well as subtitles in `result.srt`:
+
 ```bash
 echogarden speak-file text.txt result.mp3 result.wav result.srt --engine=kokoro --speed=1.1
 ```
 
 Synthesize a web page (it will try to extract its main article parts and omit the rest):
+
 ```bash
 echogarden speak-url https://example.com/hola
 ```
 
 Synthesize a Wikipedia article, in any of its language editions:
+
 ```bash
 echogarden speak-wikipedia "Psychologie" --language=fr
 ```
@@ -65,11 +75,13 @@ echogarden speak-wikipedia "Psychologie" --language=fr
 **Task**: Given an audio recording containing speech, find a textual transcription that best matches it.
 
 This would transcribe the audio file `speech.mp3`, and then play the audio, along with the recognized text, in the terminal:
+
 ```bash
 echogarden transcribe speech.mp3
 ```
 
 This would transcribe the audio file `speech.mp3` and store the resulting transcription in `result.txt`, subtitles in `result.srt`, and a full timeline tree in `result.json`:
+
 ```bash
 echogarden transcribe speech.mp3 result.txt result.srt result.json
 ```
@@ -79,11 +91,13 @@ echogarden transcribe speech.mp3 result.txt result.srt result.json
 **Task**: Given an audio file and its transcript, try to approximate the timing of the start and end of each spoken word (and its subparts).
 
 This would align the audio file `speech.mp3` with the transcript provided in `transcript.txt`, and would play the synchronized result in the terminal:
+
 ```bash
 echogarden align speech.mp3 transcript.txt
 ```
 
 This would align the audio file `speech.mp3` with the transcript provided in `transcript.txt`, and store the resulting subtitles in `result.srt`, and a full timeline tree in `result.json`:
+
 ```bash
 echogarden align speech.mp3 transcript.txt result.srt result.json
 ```
@@ -93,11 +107,13 @@ echogarden align speech.mp3 transcript.txt result.srt result.json
 **Task**: Given an audio file containing speech in one language, transcribe it to a second language. The translated transcript should be generated directly from the speech itself, without an intermediate textual translation step.
 
 This will detect the spoken language, apply speech translation to English, and play the original audio, synced with the translated transcript:
+
 ```bash
 echogarden translate-speech speech.mp3
 ```
 
 To specify the source and target languages explicitly, use the `sourceLanguage` and `targetLanguage` options:
+
 ```bash
 echogarden translate-speech speech.mp3 translation.txt --sourceLanguage=es --targetLanguage=en
 ```
@@ -107,19 +123,23 @@ echogarden translate-speech speech.mp3 translation.txt --sourceLanguage=es --tar
 ## Speech-to-translated-transcript alignment
 
 ### Direct alignment (English target only)
+
 **Task**: Given a spoken audio file and its English translated transcript, try to approximate the timing of the start and end of each translated word.
 
 This would align the audio file `dutch-speech.mp3` with the translated transcript provided in `english-translation.txt`, and would play the synchronized result in the terminal:
+
 ```bash
 echogarden align-translation dutch-speech.mp3 english-translation.txt
 ```
 
 This would align the audio file `dutch-speech.mp3` with the translated transcript provided in `english-translation.txt`, and store the resulting subtitles in `result.srt`, and a full timeline tree in `result.json`:
+
 ```bash
 echogarden align-translation dutch-speech.mp3 english-translation.txt result.srt result.json
 ```
 
 ### Two-stage alignment (any of 96 source and target languages, combined stages)
+
 **Task**: Given a spoken audio file, its transcript, and its translated transcript, try to approximate the timing of the start and end of each translated word.
 
 This would align the audio file `dutch-speech.mp3` with the Dutch (native language) transcript provided in `dutch-transcript.txt` and the translated transcript provided in `russian-translation.txt`, and would play the synchronized result in the terminal:
@@ -153,6 +173,7 @@ This manual two-step approach allows to reuse the already-aligned transcript in
 **Stage 1**:
 
 Align the audio with its native language transcript, to produce a timeline in the native language:
+
 ```bash
 echogarden align dutch-speech.mp3 dutch-transcript.txt dutch-timeline.json
 ```
@@ -167,22 +188,24 @@ echogarden align-timeline-translation dutch-timeline.json russian-transcript.txt
 
 (`--audio` is only used for previewing the result in the terminal. Otherwise, it is not necessary)
 
-
 ## Language detection
 
 **Task**: Given audio or textual input, try to identify which language it is spoken or written in.
 
 Try to identify the language of an audio file containing speech, and print the probabilities to the terminal:
+
 ```bash
 echogarden detect-speech-language speech.mp3
 ```
 
 Try to identify the language of a text file, and print the probabilities to the terminal:
+
 ```bash
 echogarden detect-text-language story.txt
 ```
 
 Try to identify the language of a text file, and store the detailed probabilities in a JSON file:
+
 ```bash
 echogarden detect-text-language story.txt detection-results.json
 ```
@@ -192,11 +215,13 @@ echogarden detect-text-language story.txt detection-results.json
 **Task**: Given an audio file, try to classify which parts of the audio contain speech, and which don't.
 
 This would apply VAD and play the audio, synchronized with `speech` and `nonspeech` indicators, printed to the terminal.
+
 ```bash
 echogarden detect-voice-activity speech.mp3
 ```
 
 This would apply VAD and store the results in a timeline JSON file.
+
 ```bash
 echogarden detect-voice-activity speech.mp3 timeline.json
 ```
@@ -206,11 +231,13 @@ echogarden detect-voice-activity speech.mp3 timeline.json
 **Task**: Attempt to reduce the amount of background noise in a spoken recording.
 
 This would apply denoising and play the denoised audio:
+
 ```bash
 echogarden denoise speech.mp3
 ```
 
 This would apply denoising, and save the denoised audio to a file:
+
 ```bash
 echogarden denoise speech.mp3 denoised-speech.mp3
 ```
@@ -220,16 +247,19 @@ echogarden denoise speech.mp3 denoised-speech.mp3
 **Task**: Try to isolate a vocal track (or other type of track, depending on model used), from the audio.
 
 This would apply source separation and play the isolated audio:
+
 ```bash
 echogarden isolate voice-with-music.mp3
 ```
 
 This would apply source separation, and save both the isolated and background audio:
+
 ```bash
 echogarden isolate voice-with-music.mp3 voice-isolated.mp3
 ```
 
 Written files would be:
+
 ```
 voice-isolated.mp3
 voice-isolated.background.mp3
@@ -256,12 +286,15 @@ echogarden align speech.mp3 transcript.txt parts/[segment].m4a parts/[segment].s
 Splitting based on sentences, using a `[sentence]` placeholder, is currently on the to-do list. Please let me know if you find this feature important, and I'll prioritize it.
 
 ## Audio playback
+
 By default, audio isn't played in the terminal when an output file is specified, you can override this behavior by adding `--play`:
+
 ```bash
 echogarden speak-file text.txt result.mp3 --play
 ```
 
 Or similarly prevent playback using `--no-play`:
+
 ```bash
 echogarden transcribe speech.mp3 --no-play
 ```
@@ -281,6 +314,7 @@ When a file named `echogarden.config` is found at the current directory, it will
 The configuration file format is simple and has a dedicated section for each command (all `speak-` commands are grouped together under `speak`), `global` section for global API options, and `cli` for common CLI options. `#` is used as a comment character.
 
 Example:
+
 ```conf
 [global]
 
@@ -324,6 +358,7 @@ whisper.temperature = 0.15
 You can also use a JSON configuration file format instead, if preferred.
 
 Name your file `echogarden.config.json`:
+
 ```json
 {
 	"speak": {
@@ -342,6 +377,7 @@ Name your file `echogarden.config.json`:
 ```
 
 Flattened property names are also accepted:
+
 ```json
 {
 	"transcribe": {
@@ -351,7 +387,6 @@ Flattened property names are also accepted:
 }
 ```
 
-
 ## Information and lists
 
 ### `list-engines`
@@ -371,6 +406,7 @@ echogarden list-voices google-cloud
 ```
 
 Saves the voice list in a JSON file:
+
 ```bash
 echogarden list-voices google-cloud google-cloud-voices.json
 ```
@@ -390,4 +426,3 @@ Uninstall one or more packages
 ### `list-packages`
 
 Show a list of installed packages
-

package/docs/Contributing.md

@@ -11,6 +11,7 @@ First, check the issue tracker, as well as the [task list](Tasklist.md) to see i
 If you find the issue you're encountering in the task list, you can still open an issue to discuss it. This allows me to know that someone cares about a particular issue, and I may give it higher priority.
 
 There might be some obvious errors that have gone unreported. Especially if:
+
 * You're using the macOS architecture: I don't have access to a macOS machine, so personally, I did not and cannot perform testing on that platform.
 * You're using cloud services: There may be changes in the service that will require updating the code. I don't often test they work correctly, since my trial periods in Google, Microsoft and Amazon have all expired, thus testing requires me to use paid requests.
 
@@ -32,7 +33,6 @@ If the problem is serious, you can report it, and we'll see what we can do.
 
 See the guide for [setting up a development environment](Development.md).
 
-
 ## Notes about licensing
 
 The code is currently licensed under GPL-v3, mainly due to one of its core dependencies, [eSpeak-NG](https://github.com/espeak-ng/espeak-ng), having this license.