Add the VOX prosody preference and panel controls

poc/src/control-bridge.ts

@@ -561,10 +561,26 @@ function buildServer(): McpServer {
                 highpass: z.number().min(40).max(400).optional().describe("High-pass filter Hz"),
                 echo: z.number().min(0).max(100).optional().describe("Mono echo amount"),
                 words: z.boolean().optional().describe("Synthesize each word and merge with gaps"),
-                wordGapMs: z.number().min(0).max(500).optional().describe("Silence between words in ms")
+                wordGapMs: z.number().min(0).max(500).optional().describe("Silence between words in ms"),
+                vox: z.boolean().optional().describe("NetTTS-style VOX prosody (Flextalk voices)"),
+                voxClean: z.boolean().optional().describe("VOX without the staccato wrapper")
             }
         },
-        async ({ text, provider, voice, speed, pitch, expression, profile, highpass, echo, words, wordGapMs }) =>
+        async ({
+            text,
+            provider,
+            voice,
+            speed,
+            pitch,
+            expression,
+            profile,
+            highpass,
+            echo,
+            words,
+            wordGapMs,
+            vox,
+            voxClean
+        }) =>
             jsonText(
                 await audio.speak(text, {
                     provider,
@@ -576,7 +592,9 @@ function buildServer(): McpServer {
                     highpass,
                     echo,
                     words,
-                    wordGapMs
+                    wordGapMs,
+                    vox,
+                    voxClean
                 })
             )
     );

poc/src/preferences.ts

@@ -30,6 +30,10 @@ export interface TtsPreferences {
     words: boolean;
     /** Silence between words in milliseconds, 0-500. */
     wordGapMs: number | null;
+    /** NetTTS-style VOX prosody (Flextalk voices only). */
+    vox: boolean;
+    /** VOX without the staccato wrapper. */
+    voxClean: boolean;
 }
 
 const PROFILE_RANGES: Record<string, [number, number]> = {
@@ -146,7 +150,9 @@ const DEFAULTS: WebPreferences = {
         highpass: null,
         echo: null,
         words: false,
-        wordGapMs: null
+        wordGapMs: null,
+        vox: false,
+        voxClean: false
     },
     audio: { duck: true },
     favourites: { users: [], channels: [] },
@@ -340,7 +346,9 @@ export class PreferencesStore {
                 highpass: normalizeRange(patch.tts?.highpass, 40, 400),
                 echo: normalizeRange(patch.tts?.echo, 0, 100),
                 words: patch.tts?.words === true,
-                wordGapMs: normalizeRange(patch.tts?.wordGapMs, 0, 500)
+                wordGapMs: normalizeRange(patch.tts?.wordGapMs, 0, 500),
+                vox: patch.tts?.vox === true,
+                voxClean: patch.tts?.voxClean === true
             };
         }
 
@@ -405,7 +413,9 @@ export class PreferencesStore {
                 highpass: normalizeRange(raw?.tts?.highpass, 40, 400),
                 echo: normalizeRange(raw?.tts?.echo, 0, 100),
                 words: raw?.tts?.words === true,
-                wordGapMs: normalizeRange(raw?.tts?.wordGapMs, 0, 500)
+                wordGapMs: normalizeRange(raw?.tts?.wordGapMs, 0, 500),
+                vox: raw?.tts?.vox === true,
+                voxClean: raw?.tts?.voxClean === true
             },
             audio: {
                 duck: raw?.audio?.duck !== false

poc/src/tts.ts

@@ -34,6 +34,10 @@ export interface TtsOptions {
     words?: boolean;
     /** Silence between words in milliseconds, 0 to 500. */
     wordGapMs?: number;
+    /** NetTTS-style VOX prosody (Flextalk voices only). */
+    vox?: boolean;
+    /** VOX without the staccato wrapper. */
+    voxClean?: boolean;
 }
 
 export interface TtsEngine {
@@ -348,6 +352,8 @@ export class Tts {
                           .replace("{echo}", options.echo !== undefined ? String(options.echo) : "")
                           .replace("{words}", options.words ? "1" : "")
                           .replace("{word_gap_ms}", options.wordGapMs !== undefined ? String(options.wordGapMs) : "")
+                          .replace("{vox}", options.vox ? "1" : "")
+                          .replace("{vox_clean}", options.voxClean ? "1" : "")
                   )
             : ["espeak-ng", ...(options.voice ? ["-v", options.voice] : []), "-w", out, "-f", textFile];
 
@@ -371,7 +377,9 @@ export class Tts {
                     ...(options.words ? { VESKSLOP_TTS_WORDS: "1" } : {}),
                     ...(options.wordGapMs !== undefined
                         ? { VESKSLOP_TTS_WORD_GAP_MS: String(options.wordGapMs) }
-                        : {})
+                        : {}),
+                    ...(options.vox ? { VESKSLOP_TTS_VOX: "1" } : {}),
+                    ...(options.voxClean ? { VESKSLOP_TTS_VOX_CLEAN: "1" } : {})
                 },
                 stdio: ["ignore", "ignore", "pipe"]
             });

poc/src/webui.ts

@@ -508,7 +508,9 @@ export function startWebUi(deps: WebUiDeps): WebUiHandle {
                     highpass: tts?.highpass ?? null,
                     echo: tts?.echo ?? null,
                     words: tts?.words === true,
-                    wordGapMs: tts?.wordGapMs ?? null
+                    wordGapMs: tts?.wordGapMs ?? null,
+                    vox: tts?.vox === true,
+                    voxClean: tts?.voxClean === true
                 };
             }
 
@@ -756,6 +758,8 @@ export function startWebUi(deps: WebUiDeps): WebUiHandle {
             const words = req.body?.words !== undefined ? req.body.words === true : prefs.tts.words;
             const wordGapMs =
                 req.body?.wordGapMs !== undefined ? Number(req.body.wordGapMs) : prefs.tts.wordGapMs ?? undefined;
+            const vox = req.body?.vox !== undefined ? req.body.vox === true : prefs.tts.vox;
+            const voxClean = req.body?.voxClean !== undefined ? req.body.voxClean === true : prefs.tts.voxClean;
 
             const result = await deps.audio.speak(text, {
                 provider: provider ?? undefined,
@@ -767,7 +771,9 @@ export function startWebUi(deps: WebUiDeps): WebUiHandle {
                 ...(Number.isFinite(highpass) ? { highpass } : {}),
                 ...(Number.isFinite(echo) ? { echo } : {}),
                 ...(words ? { words: true } : {}),
-                ...(Number.isFinite(wordGapMs) ? { wordGapMs } : {})
+                ...(Number.isFinite(wordGapMs) ? { wordGapMs } : {}),
+                ...(vox ? { vox: true } : {}),
+                ...(voxClean ? { voxClean: true } : {})
             });
             deps.getPuppet()?.appendAction({
                 type: "audio",