Files
stack/apps/web/src/components/speech/SpeechSettings.tsx
Jason Woltje bc86947d01
All checks were successful
ci/woodpecker/push/web Pipeline was successful
feat(#404): add speech settings page with provider config
Implements the SpeechSettings component with four sections:
- STT settings (enable/disable, language preference)
- TTS settings (enable/disable, voice selector, tier preference, auto-play, speed control)
- Voice preview with test button
- Provider status with health indicators

Also adds Slider UI component and getHealthStatus API client function.
30 unit tests covering all sections, toggles, voice loading, and PDA-friendly design.

Fixes #404

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-15 03:16:27 -06:00

405 lines
14 KiB
TypeScript

/**
* SpeechSettings Component
*
* Settings page for configuring speech preferences per workspace.
* Includes STT settings, TTS settings, voice preview, and provider status.
*
* Follows PDA-friendly design: calm colors, no aggressive language.
*
* Issue #404
*/
"use client";
import { useState, useEffect, useCallback } from "react";
import type { ReactElement } from "react";
import { Card, CardHeader, CardContent, CardTitle, CardDescription } from "@/components/ui/card";
import { Switch } from "@/components/ui/switch";
import { Label } from "@/components/ui/label";
import { Button } from "@/components/ui/button";
import { Slider } from "@/components/ui/slider";
import {
Select,
SelectTrigger,
SelectValue,
SelectContent,
SelectItem,
} from "@/components/ui/select";
import { getVoices, getHealthStatus } from "@/lib/api/speech";
import type { VoiceInfo, HealthResponse } from "@/lib/api/speech";
import { useTextToSpeech } from "@/hooks/useTextToSpeech";
/** Supported languages for STT */
const STT_LANGUAGES = [
{ value: "en", label: "English" },
{ value: "es", label: "Spanish" },
{ value: "fr", label: "French" },
{ value: "de", label: "German" },
{ value: "it", label: "Italian" },
{ value: "pt", label: "Portuguese" },
{ value: "ja", label: "Japanese" },
{ value: "zh", label: "Chinese" },
{ value: "ko", label: "Korean" },
{ value: "auto", label: "Auto-detect" },
];
/** TTS tier options */
const TIER_OPTIONS = [
{ value: "default", label: "Default" },
{ value: "premium", label: "Premium" },
{ value: "fallback", label: "Fallback" },
];
/** Sample text for voice preview */
const PREVIEW_TEXT = "Hello, this is a preview of the selected voice. How does it sound?";
/**
* SpeechSettings provides a comprehensive settings interface for
* configuring speech-to-text and text-to-speech preferences.
*/
export function SpeechSettings(): ReactElement {
// STT state
const [sttEnabled, setSttEnabled] = useState(true);
const [sttLanguage, setSttLanguage] = useState("en");
// TTS state
const [ttsEnabled, setTtsEnabled] = useState(true);
const [selectedVoice, setSelectedVoice] = useState("");
const [selectedTier, setSelectedTier] = useState("default");
const [autoPlay, setAutoPlay] = useState(false);
const [speed, setSpeed] = useState(1.0);
// Data state
const [voices, setVoices] = useState<VoiceInfo[]>([]);
const [voicesError, setVoicesError] = useState<string | null>(null);
const [healthData, setHealthData] = useState<HealthResponse["data"] | null>(null);
const [healthError, setHealthError] = useState<string | null>(null);
// Preview hook
const {
synthesize,
audioUrl,
isLoading: isPreviewLoading,
error: previewError,
} = useTextToSpeech();
/**
* Fetch available voices from the API
*/
const fetchVoices = useCallback(async (): Promise<void> => {
try {
setVoicesError(null);
const response = await getVoices();
setVoices(response.data);
// Select the first default voice if none selected
if (response.data.length > 0 && !selectedVoice) {
const defaultVoice = response.data.find((v) => v.isDefault);
const firstVoice = response.data[0];
setSelectedVoice(defaultVoice?.id ?? firstVoice?.id ?? "");
}
} catch {
setVoicesError("Unable to load voices. Please try again later.");
}
}, [selectedVoice]);
/**
* Fetch health status from the API
*/
const fetchHealth = useCallback(async (): Promise<void> => {
try {
setHealthError(null);
const response = await getHealthStatus();
setHealthData(response.data);
} catch {
setHealthError("Unable to check provider status. Please try again later.");
}
}, []);
// Fetch voices and health on mount
useEffect(() => {
void fetchVoices();
void fetchHealth();
}, [fetchVoices, fetchHealth]);
/**
* Handle voice preview test
*/
const handleTestVoice = useCallback(async (): Promise<void> => {
const options: Record<string, string | number> = {
speed,
tier: selectedTier,
};
if (selectedVoice) {
options.voice = selectedVoice;
}
await synthesize(PREVIEW_TEXT, options);
}, [synthesize, selectedVoice, speed, selectedTier]);
return (
<div className="space-y-6">
<div>
<h2 className="text-2xl font-semibold text-gray-900">Speech Settings</h2>
<p className="text-sm text-gray-600 mt-1">
Configure voice input and output preferences for your workspace
</p>
</div>
{/* STT Settings */}
<Card>
<CardHeader>
<CardTitle className="text-lg">Speech-to-Text</CardTitle>
<CardDescription>Configure voice input preferences</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-4">
{/* Enable STT Toggle */}
<div className="flex items-center justify-between">
<div className="space-y-0.5">
<Label htmlFor="stt-enabled">Enable Speech-to-Text</Label>
<p className="text-xs text-gray-500">
Allow voice input for text fields and commands
</p>
</div>
<Switch
id="stt-enabled"
checked={sttEnabled}
onCheckedChange={setSttEnabled}
aria-label="Enable Speech-to-Text"
/>
</div>
{/* Language Preference */}
<div className="space-y-2">
<Label htmlFor="stt-language">Language</Label>
<Select value={sttLanguage} onValueChange={setSttLanguage}>
<SelectTrigger id="stt-language" className="w-full">
<SelectValue placeholder="Select language" />
</SelectTrigger>
<SelectContent>
{STT_LANGUAGES.map((lang) => (
<SelectItem key={lang.value} value={lang.value}>
{lang.label}
</SelectItem>
))}
</SelectContent>
</Select>
</div>
</div>
</CardContent>
</Card>
{/* TTS Settings */}
<Card>
<CardHeader>
<CardTitle className="text-lg">Text-to-Speech</CardTitle>
<CardDescription>Configure voice output preferences</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-4">
{/* Enable TTS Toggle */}
<div className="flex items-center justify-between">
<div className="space-y-0.5">
<Label htmlFor="tts-enabled">Enable Text-to-Speech</Label>
<p className="text-xs text-gray-500">
Allow reading content aloud with synthesized voice
</p>
</div>
<Switch
id="tts-enabled"
checked={ttsEnabled}
onCheckedChange={setTtsEnabled}
aria-label="Enable Text-to-Speech"
/>
</div>
{/* Default Voice Selector */}
<div className="space-y-2">
<Label htmlFor="tts-voice">Default Voice</Label>
{voicesError ? (
<p className="text-sm text-amber-600">{voicesError}</p>
) : (
<Select value={selectedVoice} onValueChange={setSelectedVoice}>
<SelectTrigger id="tts-voice" className="w-full">
<SelectValue placeholder="Select a voice" />
</SelectTrigger>
<SelectContent>
{voices.map((voice) => (
<SelectItem key={voice.id} value={voice.id}>
{voice.name}
</SelectItem>
))}
</SelectContent>
</Select>
)}
</div>
{/* Provider Tier Preference */}
<div className="space-y-2">
<Label htmlFor="tts-tier">Provider Tier</Label>
<p className="text-xs text-gray-500">
Choose the preferred quality tier for voice synthesis
</p>
<Select value={selectedTier} onValueChange={setSelectedTier}>
<SelectTrigger id="tts-tier" className="w-full">
<SelectValue placeholder="Select tier" />
</SelectTrigger>
<SelectContent>
{TIER_OPTIONS.map((tier) => (
<SelectItem key={tier.value} value={tier.value}>
{tier.label}
</SelectItem>
))}
</SelectContent>
</Select>
</div>
{/* Auto-play Toggle */}
<div className="flex items-center justify-between">
<div className="space-y-0.5">
<Label htmlFor="tts-autoplay">Auto-play</Label>
<p className="text-xs text-gray-500">
Automatically play TTS responses when received
</p>
</div>
<Switch
id="tts-autoplay"
checked={autoPlay}
onCheckedChange={setAutoPlay}
aria-label="Auto-play"
/>
</div>
{/* Speed Control */}
<div className="space-y-2">
<div className="flex items-center justify-between">
<Label htmlFor="tts-speed">Speed</Label>
<span className="text-sm text-gray-600">{speed.toFixed(1)}x</span>
</div>
<Slider
id="tts-speed"
min={0.5}
max={2}
step={0.1}
value={[speed]}
onValueChange={(values) => {
const newSpeed = values[0];
if (newSpeed !== undefined) {
setSpeed(newSpeed);
}
}}
/>
<div className="flex justify-between text-xs text-gray-400">
<span>0.5x</span>
<span>1.0x</span>
<span>2.0x</span>
</div>
</div>
</div>
</CardContent>
</Card>
{/* Voice Preview */}
<Card>
<CardHeader>
<CardTitle className="text-lg">Voice Preview</CardTitle>
<CardDescription>Preview the selected voice with sample text</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-3">
<p className="text-sm text-gray-600 italic">&ldquo;{PREVIEW_TEXT}&rdquo;</p>
<Button
variant="outline"
size="sm"
onClick={() => void handleTestVoice()}
disabled={isPreviewLoading}
aria-label="Test voice"
>
{isPreviewLoading ? "Synthesizing..." : "Test Voice"}
</Button>
{previewError && <p className="text-sm text-amber-600">{previewError}</p>}
{audioUrl && (
<audio controls src={audioUrl} className="w-full mt-2">
<track kind="captions" />
</audio>
)}
</div>
</CardContent>
</Card>
{/* Provider Status */}
<Card>
<CardHeader>
<CardTitle className="text-lg">Provider Status</CardTitle>
<CardDescription>Current availability of speech service providers</CardDescription>
</CardHeader>
<CardContent>
<div className="space-y-3" data-testid="provider-status">
{healthError ? (
<p className="text-sm text-amber-600">{healthError}</p>
) : healthData ? (
<>
{/* STT Provider */}
<div className="flex items-center justify-between py-2">
<span className="text-sm text-gray-700">Speech-to-Text Provider</span>
<div className="flex items-center gap-2">
{healthData.stt.available ? (
<>
<span
className="inline-block h-2.5 w-2.5 rounded-full bg-green-500"
data-testid="status-active"
aria-label="Active"
/>
<span className="text-sm text-gray-600">Active</span>
</>
) : (
<>
<span
className="inline-block h-2.5 w-2.5 rounded-full bg-gray-400"
data-testid="status-inactive"
aria-label="Inactive"
/>
<span className="text-sm text-gray-600">Inactive</span>
</>
)}
</div>
</div>
{/* TTS Provider */}
<div className="flex items-center justify-between py-2">
<span className="text-sm text-gray-700">Text-to-Speech Provider</span>
<div className="flex items-center gap-2">
{healthData.tts.available ? (
<>
<span
className="inline-block h-2.5 w-2.5 rounded-full bg-green-500"
data-testid="status-active"
aria-label="Active"
/>
<span className="text-sm text-gray-600">Active</span>
</>
) : (
<>
<span
className="inline-block h-2.5 w-2.5 rounded-full bg-gray-400"
data-testid="status-inactive"
aria-label="Inactive"
/>
<span className="text-sm text-gray-600">Inactive</span>
</>
)}
</div>
</div>
</>
) : (
<p className="text-sm text-gray-500">Checking provider status...</p>
)}
</div>
</CardContent>
</Card>
</div>
);
}
export default SpeechSettings;