feat(audio): choose a male or female local voice per language

The installer now fetches one male and one female Piper voice per language (Swedish
NST/Lisa, English Ryan/Lessac), with genders confirmed by measuring each voice's pitch
rather than guessed from the name. Settings -> Audio gets a voice selector per language
with its own Test button that always plays the Piper voice. Male is preselected for both.

The integration test now runs its server with an empty home directory, so voices
installed on the developer's own machine can't leak into it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
larssandandClaude Opus 5.5 committed 2026-09-27 20:29:59 +02:00
1 parent e8a2799a92
commit 196437d25b
17 files changed
+167 -38

No files matched your search

+56 -8
View File
@@ -1,6 +1,8 @@
// "Voice engine" panel in Settings -> Audio: choose browser voices or the local Piper
// voices, install Piper + Swedish/English voices once, and pre-generate fixed phrases and
// driver names so race day never waits on generation.
import { speakWithPiper } from "./piper_speech.js";
const LANGUAGES = ["sv", "en"];
// Fixed per language on purpose - the sample must be in the voice being tested, not the UI language.
const SAMPLES = { sv: "Heat ett startar om tio sekunder. Nytt varvrekord för Alex Karlsson.", en: "Heat one starts in ten seconds. New lap record for Alex Karlsson." };
@@ -9,16 +11,19 @@ async function getStatus() {
return fetch("/api/tts/status").then((res) => res.json()).catch(() => null);
}
const voiceSettingKey = (language) => (language === "sv" ? "ttsVoiceSv" : "ttsVoiceEn");
async function buildPregenerateItems(state) {
const manifest = await fetch("/race-sounds/sound_manifest.json").then((res) => res.json()).catch(() => ({}));
const items = [];
LANGUAGES.forEach((language) => {
const voice = state.settings[voiceSettingKey(language)] || "";
Object.values(manifest?.voice_events?.[language] || {})
.filter((text) => typeof text === "string" && text && !text.includes("{"))
.forEach((text) => items.push({ text, language }));
.forEach((text) => items.push({ text, language, voice }));
(state.drivers || []).forEach((driver) => {
const name = String(driver.speechName || driver.name || "").trim();
if (name) items.push({ text: name, language });
if (name) items.push({ text: name, language, voice });
});
});
return items;
@@ -30,7 +35,25 @@ export async function mountTtsSettings(container, deps) {
const status = await getStatus();
if (!container.isConnected) return;
const remount = () => mountTtsSettings(container, deps);
const hasLanguage = (language) => Boolean(status?.voices?.some((voice) => voice.language === language));
const voicesFor = (language) => (status?.voices || []).filter((voice) => voice.language === language);
const hasLanguage = (language) => voicesFor(language).length > 0;
// Complete = a male and a female voice installed for every language.
const complete = LANGUAGES.every((language) => ["male", "female"].every((gender) => voicesFor(language).some((voice) => voice.gender === gender)));
const voiceLabel = (voice) => (voice.gender ? `${voice.label} (${t(voice.gender === "male" ? "tts.gender_male" : "tts.gender_female")})` : voice.label);
const voiceSelect = (language) => {
const chosen = state.settings[voiceSettingKey(language)] || "";
const automatic = voicesFor(language).find((voice) => voice.isDefault) || voicesFor(language)[0];
return `
<div class="tts-voice-row">
<label><span>${escapeHtml(t(language === "sv" ? "tts.voice_sv" : "tts.voice_en"))}</span>
<select data-tts-voice="${language}" ${hasLanguage(language) ? "" : "disabled"}>
<option value="">${escapeHtml(t("tts.voice_auto"))}${automatic ? ` - ${escapeHtml(voiceLabel(automatic))}` : ""}</option>
${voicesFor(language).map((voice) => `<option value="${escapeHtml(voice.name)}" ${chosen === voice.name ? "selected" : ""}>${escapeHtml(voiceLabel(voice))}</option>`).join("")}
</select>
</label>
<button class="btn" type="button" data-tts-test="${language}" ${hasLanguage(language) ? "" : "disabled"}>${escapeHtml(t("tts.test"))}</button>
</div>`;
};
const engine = state.settings.ttsEngine === "piper" ? "piper" : "browser";
const install = status?.install || {};
const pregen = status?.pregenerate || {};
@@ -51,10 +74,14 @@ export async function mountTtsSettings(container, deps) {
</div>
</div>
<div class="actions">
<button class="btn" type="button" id="ttsInstall" ${busy ? "disabled" : ""}>${escapeHtml(t(status?.available && hasLanguage("sv") && hasLanguage("en") ? "tts.reinstall" : "tts.install"))}</button>
<button class="btn" type="button" id="ttsInstall" ${busy ? "disabled" : ""}>${escapeHtml(t(status?.available && complete ? "tts.reinstall" : "tts.install"))}</button>
<button class="btn" type="button" id="ttsPregenerate" ${busy || !status?.available ? "disabled" : ""}>${escapeHtml(t("tts.pregenerate"))}</button>
<button class="btn" type="button" id="ttsTest" ${!status?.available ? "disabled" : ""}>${escapeHtml(t("tts.test"))}</button>
</div>
<div class="form-grid cols-2 mt-16">
${voiceSelect("sv")}
${voiceSelect("en")}
</div>
<p class="error" id="ttsTestError" hidden></p>
${install.running || install.log?.length ? `<pre class="log-box">${escapeHtml((install.log || []).join("\n"))}${install.error ? `\n${escapeHtml(install.error)}` : ""}</pre>` : ""}
${pregen.total ? `<p class="hint">${escapeHtml(t("tts.pregenerate_progress", { done: pregen.done, total: pregen.total, failed: pregen.failed }))}</p>` : ""}`;
@@ -70,9 +97,30 @@ export async function mountTtsSettings(container, deps) {
await fetch("/api/tts/pregenerate", { method: "POST", headers: { "Content-Type": "application/json" }, body: JSON.stringify({ items: await buildPregenerateItems(state) }) });
remount();
});
container.querySelector("#ttsTest").addEventListener("click", () => {
const language = state.settings.raceAudio?.language === "en" ? "en" : "sv";
speakText(SAMPLES[language], { interrupt: true, language });
container.querySelectorAll("[data-tts-voice]").forEach((select) => {
select.addEventListener("change", () => {
state.settings[voiceSettingKey(select.dataset.ttsVoice)] = select.value;
saveState();
});
});
// Always tests the Piper voice itself (no browser fallback), whatever engine is active,
// so picking a voice and hearing it are never confused with the browser's voice.
container.querySelectorAll("[data-tts-test]").forEach((button) => {
button.addEventListener("click", () => {
const language = button.dataset.ttsTest;
const error = container.querySelector("#ttsTestError");
error.hidden = true;
speakWithPiper(SAMPLES[language], {
language,
voice: state.settings[voiceSettingKey(language)] || "",
interrupt: true,
fallback: () => {
error.textContent = t("tts.test_failed");
error.hidden = false;
return true;
},
});
});
});
// Keep polling while a background install/pre-generation is running.
if (busy) setTimeout(() => { if (container.isConnected) remount(); }, 1500);