feat(#403): add audio playback component for TTS output
All checks were successful
ci/woodpecker/push/web Pipeline was successful

Implements AudioPlayer inline component with play/pause, progress bar,
speed control (0.5x-2x), download, and duration display. Adds
TextToSpeechButton "Read aloud" component that synthesizes text via
the speech API and integrates AudioPlayer for playback. Includes
useTextToSpeech hook with API integration, audio caching, and
playback state management. All 32 tests passing.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-02-15 03:05:39 -06:00
parent 28c9e6fe65
commit 74d6c1092e
14 changed files with 2664 additions and 0 deletions

View File

@@ -0,0 +1,178 @@
/**
* @file AudioPlayer.test.tsx
* @description Tests for the AudioPlayer component that provides inline TTS audio playback
*/
import { describe, it, expect, vi, beforeEach } from "vitest";
import { render, screen } from "@testing-library/react";
import userEvent from "@testing-library/user-event";
import { AudioPlayer } from "./AudioPlayer";
// Mock HTMLAudioElement
class MockAudio {
src = "";
currentTime = 0;
duration = 60;
paused = true;
playbackRate = 1;
volume = 1;
onended: (() => void) | null = null;
ontimeupdate: (() => void) | null = null;
onloadedmetadata: (() => void) | null = null;
onerror: ((e: unknown) => void) | null = null;
play(): Promise<void> {
this.paused = false;
return Promise.resolve();
}
pause(): void {
this.paused = true;
}
addEventListener(event: string, handler: () => void): void {
if (event === "ended") this.onended = handler;
if (event === "timeupdate") this.ontimeupdate = handler;
if (event === "loadedmetadata") this.onloadedmetadata = handler;
if (event === "error") this.onerror = handler;
}
removeEventListener(): void {
// no-op for tests
}
}
vi.stubGlobal("Audio", MockAudio);
describe("AudioPlayer", () => {
beforeEach(() => {
vi.clearAllMocks();
});
describe("rendering", () => {
it("should render play button", () => {
render(<AudioPlayer src="blob:test-audio" />);
const playButton = screen.getByRole("button", { name: "Play audio" });
expect(playButton).toBeInTheDocument();
});
it("should render download button", () => {
render(<AudioPlayer src="blob:test-audio" />);
const downloadButton = screen.getByRole("button", { name: /download/i });
expect(downloadButton).toBeInTheDocument();
});
it("should render time display showing 0:00", () => {
render(<AudioPlayer src="blob:test-audio" />);
expect(screen.getByText("0:00")).toBeInTheDocument();
});
it("should render speed control", () => {
render(<AudioPlayer src="blob:test-audio" />);
const speedButton = screen.getByRole("button", { name: "Playback speed" });
expect(speedButton).toBeInTheDocument();
});
it("should render progress bar", () => {
render(<AudioPlayer src="blob:test-audio" />);
const progressBar = screen.getByRole("progressbar");
expect(progressBar).toBeInTheDocument();
});
it("should not render when src is null", () => {
const { container } = render(<AudioPlayer src={null} />);
expect(container.firstChild).toBeNull();
});
});
describe("play/pause", () => {
it("should toggle to pause button when playing", async () => {
const user = userEvent.setup();
render(<AudioPlayer src="blob:test-audio" />);
const playButton = screen.getByRole("button", { name: "Play audio" });
await user.click(playButton);
expect(screen.getByRole("button", { name: "Pause audio" })).toBeInTheDocument();
});
});
describe("speed control", () => {
it("should cycle through speed options on click", async () => {
const user = userEvent.setup();
render(<AudioPlayer src="blob:test-audio" />);
const speedButton = screen.getByRole("button", { name: "Playback speed" });
// Default should be 1x
expect(speedButton).toHaveTextContent("1x");
// Click to go to 1.5x
await user.click(speedButton);
expect(speedButton).toHaveTextContent("1.5x");
// Click to go to 2x
await user.click(speedButton);
expect(speedButton).toHaveTextContent("2x");
// Click to go to 0.5x
await user.click(speedButton);
expect(speedButton).toHaveTextContent("0.5x");
// Click to go back to 1x
await user.click(speedButton);
expect(speedButton).toHaveTextContent("1x");
});
});
describe("accessibility", () => {
it("should have proper aria labels on controls", () => {
render(<AudioPlayer src="blob:test-audio" />);
expect(screen.getByRole("button", { name: "Play audio" })).toBeInTheDocument();
expect(screen.getByRole("button", { name: /download/i })).toBeInTheDocument();
expect(screen.getByRole("button", { name: "Playback speed" })).toBeInTheDocument();
expect(screen.getByRole("progressbar")).toHaveAttribute("aria-label");
});
it("should have region role on the player container", () => {
render(<AudioPlayer src="blob:test-audio" />);
expect(screen.getByRole("region", { name: /audio player/i })).toBeInTheDocument();
});
});
describe("design", () => {
it("should not use aggressive red colors", () => {
const { container } = render(<AudioPlayer src="blob:test-audio" />);
const allElements = container.querySelectorAll("*");
allElements.forEach((el) => {
const className = el.className;
if (typeof className === "string") {
expect(className).not.toMatch(/bg-red-|text-red-|border-red-/);
}
});
});
});
describe("callbacks", () => {
it("should call onPlayStateChange when play state changes", async () => {
const onPlayStateChange = vi.fn();
const user = userEvent.setup();
render(<AudioPlayer src="blob:test-audio" onPlayStateChange={onPlayStateChange} />);
const playButton = screen.getByRole("button", { name: "Play audio" });
await user.click(playButton);
expect(onPlayStateChange).toHaveBeenCalledWith(true);
});
});
});

View File

@@ -0,0 +1,250 @@
/**
* AudioPlayer Component
* Inline audio player for TTS content with play/pause, progress,
* speed control, download, and duration display.
*
* Follows PDA-friendly design: no aggressive colors, calm interface.
*/
import { useState, useRef, useEffect, useCallback } from "react";
import type { ReactElement } from "react";
/** Playback speed options */
const SPEED_OPTIONS = [1, 1.5, 2, 0.5] as const;
export interface AudioPlayerProps {
/** URL of the audio to play (blob URL or HTTP URL). If null, nothing renders. */
src: string | null;
/** Whether to auto-play when src changes */
autoPlay?: boolean;
/** Callback when play state changes */
onPlayStateChange?: (isPlaying: boolean) => void;
/** Optional className for the container */
className?: string;
}
/**
* Format seconds into M:SS display
*/
function formatTime(seconds: number): string {
if (!isFinite(seconds) || seconds < 0) return "0:00";
const mins = Math.floor(seconds / 60);
const secs = Math.floor(seconds % 60);
return `${String(mins)}:${String(secs).padStart(2, "0")}`;
}
/**
* AudioPlayer displays an inline audio player with controls for
* play/pause, progress tracking, speed adjustment, and download.
*/
export function AudioPlayer({
src,
autoPlay = false,
onPlayStateChange,
className = "",
}: AudioPlayerProps): ReactElement | null {
const [isPlaying, setIsPlaying] = useState(false);
const [currentTime, setCurrentTime] = useState(0);
const [duration, setDuration] = useState(0);
const [speedIndex, setSpeedIndex] = useState(0);
const audioRef = useRef<HTMLAudioElement | null>(null);
/**
* Set up audio element when src changes
*/
useEffect((): (() => void) | undefined => {
if (!src) return undefined;
const audio = new Audio(src);
audioRef.current = audio;
const onLoadedMetadata = (): void => {
if (isFinite(audio.duration)) {
setDuration(audio.duration);
}
};
const onTimeUpdate = (): void => {
setCurrentTime(audio.currentTime);
};
const onEnded = (): void => {
setIsPlaying(false);
setCurrentTime(0);
onPlayStateChange?.(false);
};
audio.addEventListener("loadedmetadata", onLoadedMetadata);
audio.addEventListener("timeupdate", onTimeUpdate);
audio.addEventListener("ended", onEnded);
if (autoPlay) {
void audio.play().then(() => {
setIsPlaying(true);
onPlayStateChange?.(true);
});
}
return (): void => {
audio.pause();
audio.removeEventListener("loadedmetadata", onLoadedMetadata);
audio.removeEventListener("timeupdate", onTimeUpdate);
audio.removeEventListener("ended", onEnded);
audioRef.current = null;
};
}, [src, autoPlay, onPlayStateChange]);
/**
* Toggle play/pause
*/
const togglePlayPause = useCallback(async (): Promise<void> => {
const audio = audioRef.current;
if (!audio) return;
if (isPlaying) {
audio.pause();
setIsPlaying(false);
onPlayStateChange?.(false);
} else {
await audio.play();
setIsPlaying(true);
onPlayStateChange?.(true);
}
}, [isPlaying, onPlayStateChange]);
/**
* Cycle through speed options
*/
const cycleSpeed = useCallback((): void => {
const nextIndex = (speedIndex + 1) % SPEED_OPTIONS.length;
setSpeedIndex(nextIndex);
const audio = audioRef.current;
if (audio) {
audio.playbackRate = SPEED_OPTIONS[nextIndex] ?? 1;
}
}, [speedIndex]);
/**
* Handle progress bar click for seeking
*/
const handleProgressClick = useCallback(
(event: React.MouseEvent<HTMLDivElement>): void => {
const audio = audioRef.current;
if (!audio || !duration) return;
const rect = event.currentTarget.getBoundingClientRect();
const clickX = event.clientX - rect.left;
const fraction = clickX / rect.width;
audio.currentTime = fraction * duration;
setCurrentTime(audio.currentTime);
},
[duration]
);
/**
* Handle download
*/
const handleDownload = useCallback((): void => {
if (!src) return;
const link = document.createElement("a");
link.href = src;
link.download = "speech-audio.mp3";
document.body.appendChild(link);
link.click();
document.body.removeChild(link);
}, [src]);
// Don't render if no source
if (!src) return null;
const progress = duration > 0 ? (currentTime / duration) * 100 : 0;
const currentSpeed = SPEED_OPTIONS[speedIndex] ?? 1;
return (
<div
role="region"
aria-label="Audio player"
className={`flex items-center gap-2 rounded-lg border border-gray-200 bg-gray-50 px-3 py-2 ${className}`}
>
{/* Play/Pause Button */}
<button
type="button"
onClick={() => void togglePlayPause()}
aria-label={isPlaying ? "Pause audio" : "Play audio"}
className="flex h-8 w-8 shrink-0 items-center justify-center rounded-full bg-blue-500 text-white transition-colors hover:bg-blue-600 focus:outline-none focus:ring-2 focus:ring-blue-300"
>
{isPlaying ? (
<svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor" aria-hidden="true">
<rect x="6" y="4" width="4" height="16" rx="1" />
<rect x="14" y="4" width="4" height="16" rx="1" />
</svg>
) : (
<svg width="14" height="14" viewBox="0 0 24 24" fill="currentColor" aria-hidden="true">
<polygon points="6,4 20,12 6,20" />
</svg>
)}
</button>
{/* Time Display */}
<span className="min-w-[3.5rem] text-xs text-gray-500 tabular-nums">
{formatTime(currentTime)}
{duration > 0 && <span className="text-gray-400"> / {formatTime(duration)}</span>}
</span>
{/* Progress Bar */}
<div
role="progressbar"
aria-label="Audio progress"
aria-valuenow={Math.round(progress)}
aria-valuemin={0}
aria-valuemax={100}
className="relative h-1.5 flex-1 cursor-pointer rounded-full bg-gray-200"
onClick={handleProgressClick}
>
<div
className="absolute left-0 top-0 h-full rounded-full bg-blue-400 transition-all"
style={{ width: `${String(Math.min(progress, 100))}%` }}
/>
</div>
{/* Speed Control */}
<button
type="button"
onClick={cycleSpeed}
aria-label="Playback speed"
className="min-w-[2.5rem] rounded px-1.5 py-0.5 text-xs font-medium text-gray-600 transition-colors hover:bg-gray-200 focus:outline-none focus:ring-2 focus:ring-blue-300"
>
{String(currentSpeed)}x
</button>
{/* Download Button */}
<button
type="button"
onClick={handleDownload}
aria-label="Download audio"
className="flex h-7 w-7 shrink-0 items-center justify-center rounded text-gray-500 transition-colors hover:bg-gray-200 hover:text-gray-700 focus:outline-none focus:ring-2 focus:ring-blue-300"
>
<svg
width="14"
height="14"
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
strokeWidth="2"
strokeLinecap="round"
strokeLinejoin="round"
aria-hidden="true"
>
<path d="M21 15v4a2 2 0 01-2 2H5a2 2 0 01-2-2v-4" />
<polyline points="7 10 12 15 17 10" />
<line x1="12" y1="15" x2="12" y2="3" />
</svg>
</button>
</div>
);
}
export default AudioPlayer;

View File

@@ -0,0 +1,70 @@
import { describe, it, expect } from "vitest";
import { render, screen } from "@testing-library/react";
import { AudioVisualizer } from "./AudioVisualizer";
describe("AudioVisualizer", (): void => {
it("should render the visualizer container", (): void => {
render(<AudioVisualizer audioLevel={0} isActive={false} />);
const container = screen.getByTestId("audio-visualizer");
expect(container).toBeInTheDocument();
});
it("should render visualization bars", (): void => {
render(<AudioVisualizer audioLevel={0.5} isActive={true} />);
const bars = screen.getAllByTestId("visualizer-bar");
expect(bars.length).toBeGreaterThan(0);
});
it("should show inactive state when not active", (): void => {
render(<AudioVisualizer audioLevel={0} isActive={false} />);
const container = screen.getByTestId("audio-visualizer");
expect(container).toBeInTheDocument();
// Bars should be at minimum height when inactive
const bars = screen.getAllByTestId("visualizer-bar");
bars.forEach((bar) => {
const style = bar.getAttribute("style");
expect(style).toContain("height");
});
});
it("should reflect audio level in bar heights when active", (): void => {
render(<AudioVisualizer audioLevel={0.8} isActive={true} />);
const bars = screen.getAllByTestId("visualizer-bar");
// At least one bar should have non-minimal height
const hasActiveBars = bars.some((bar) => {
const style = bar.getAttribute("style") ?? "";
const heightMatch = /height:\s*(\d+)/.exec(style);
return heightMatch?.[1] ? parseInt(heightMatch[1], 10) > 4 : false;
});
expect(hasActiveBars).toBe(true);
});
it("should use calm colors (no aggressive reds)", (): void => {
render(<AudioVisualizer audioLevel={0.5} isActive={true} />);
const container = screen.getByTestId("audio-visualizer");
const allElements = container.querySelectorAll("*");
allElements.forEach((el) => {
const className = (el as HTMLElement).className;
expect(className).not.toMatch(/bg-red-|text-red-/);
});
});
it("should accept custom className", (): void => {
render(<AudioVisualizer audioLevel={0.5} isActive={true} className="custom-class" />);
const container = screen.getByTestId("audio-visualizer");
expect(container.className).toContain("custom-class");
});
it("should render with configurable bar count", (): void => {
render(<AudioVisualizer audioLevel={0.5} isActive={true} barCount={8} />);
const bars = screen.getAllByTestId("visualizer-bar");
expect(bars).toHaveLength(8);
});
});

View File

@@ -0,0 +1,87 @@
/**
* AudioVisualizer component
*
* Displays a simple audio level visualization using bars.
* Uses the Web Audio API's AnalyserNode data (passed as audioLevel)
* to show microphone input levels during recording.
*
* Design: Calm, non-aggressive colors following PDA-friendly guidelines.
*/
import { useMemo } from "react";
export interface AudioVisualizerProps {
/** Current audio level (0-1) */
audioLevel: number;
/** Whether the visualizer is actively listening */
isActive: boolean;
/** Number of bars to display (default: 5) */
barCount?: number;
/** Additional CSS classes */
className?: string;
}
/**
* Generate bar heights based on audio level.
* Creates a natural-looking wave pattern where center bars are taller.
*/
function generateBarHeights(level: number, count: number): number[] {
const heights: number[] = [];
const center = (count - 1) / 2;
for (let i = 0; i < count; i++) {
// Distance from center (0-1)
const distFromCenter = Math.abs(i - center) / center;
// Center bars are taller, edge bars shorter
const multiplier = 1 - distFromCenter * 0.5;
// Min height 4px, max height 24px when active
const minHeight = 4;
const maxHeight = 24;
const height = minHeight + level * (maxHeight - minHeight) * multiplier;
heights.push(Math.round(height));
}
return heights;
}
/**
* Audio level visualizer with animated bars.
* Shows microphone input levels during voice recording.
*/
export function AudioVisualizer({
audioLevel,
isActive,
barCount = 5,
className = "",
}: AudioVisualizerProps): React.JSX.Element {
const barHeights = useMemo(() => {
if (!isActive) {
return Array.from({ length: barCount }, () => 4);
}
return generateBarHeights(audioLevel, barCount);
}, [audioLevel, isActive, barCount]);
return (
<div
data-testid="audio-visualizer"
className={`flex items-center gap-0.5 ${className}`}
role="img"
aria-label={
isActive
? `Audio level: ${String(Math.round(audioLevel * 100))}%`
: "Audio visualizer inactive"
}
>
{barHeights.map((height, index) => (
<div
key={index}
data-testid="visualizer-bar"
className={`w-1 rounded-full transition-all duration-150 ease-out ${
isActive ? "bg-sky-400" : "bg-slate-300 dark:bg-slate-600"
}`}
style={{ height: `${height.toString()}px` }}
/>
))}
</div>
);
}

View File

@@ -0,0 +1,218 @@
/**
* @file TextToSpeechButton.test.tsx
* @description Tests for the TextToSpeechButton "Read aloud" component
*/
import { describe, it, expect, vi, beforeEach } from "vitest";
import { render, screen } from "@testing-library/react";
import userEvent from "@testing-library/user-event";
import { TextToSpeechButton } from "./TextToSpeechButton";
// Mock the useTextToSpeech hook
const mockSynthesize = vi.fn();
const mockPlay = vi.fn();
const mockPause = vi.fn();
const mockStop = vi.fn();
vi.mock("@/hooks/useTextToSpeech", () => ({
useTextToSpeech: vi.fn(() => ({
synthesize: mockSynthesize,
play: mockPlay,
pause: mockPause,
stop: mockStop,
audioUrl: null,
isLoading: false,
error: null,
isPlaying: false,
duration: 0,
currentTime: 0,
})),
}));
// Import after mocking
import { useTextToSpeech } from "@/hooks/useTextToSpeech";
const mockUseTextToSpeech = useTextToSpeech as ReturnType<typeof vi.fn>;
// Mock HTMLAudioElement for AudioPlayer used inside TextToSpeechButton
class MockAudio {
src = "";
currentTime = 0;
duration = 60;
paused = true;
playbackRate = 1;
volume = 1;
onended: (() => void) | null = null;
ontimeupdate: (() => void) | null = null;
onloadedmetadata: (() => void) | null = null;
onerror: ((e: unknown) => void) | null = null;
play(): Promise<void> {
this.paused = false;
return Promise.resolve();
}
pause(): void {
this.paused = true;
}
addEventListener(): void {
// no-op
}
removeEventListener(): void {
// no-op
}
}
vi.stubGlobal("Audio", MockAudio);
describe("TextToSpeechButton", () => {
beforeEach(() => {
vi.clearAllMocks();
mockUseTextToSpeech.mockReturnValue({
synthesize: mockSynthesize,
play: mockPlay,
pause: mockPause,
stop: mockStop,
audioUrl: null,
isLoading: false,
error: null,
isPlaying: false,
duration: 0,
currentTime: 0,
});
});
describe("rendering", () => {
it("should render a read aloud button", () => {
render(<TextToSpeechButton text="Hello world" />);
const button = screen.getByRole("button", { name: /read aloud/i });
expect(button).toBeInTheDocument();
});
it("should not render AudioPlayer initially when no audio is synthesized", () => {
render(<TextToSpeechButton text="Hello world" />);
expect(screen.queryByRole("region", { name: /audio player/i })).not.toBeInTheDocument();
});
});
describe("click behavior", () => {
it("should call synthesize with text on click", async () => {
const user = userEvent.setup();
mockSynthesize.mockResolvedValueOnce(undefined);
render(<TextToSpeechButton text="Hello world" />);
const button = screen.getByRole("button", { name: /read aloud/i });
await user.click(button);
expect(mockSynthesize).toHaveBeenCalledWith("Hello world", undefined);
});
it("should pass voice and tier options when provided", async () => {
const user = userEvent.setup();
mockSynthesize.mockResolvedValueOnce(undefined);
render(<TextToSpeechButton text="Hello" voice="alloy" tier="premium" />);
const button = screen.getByRole("button", { name: /read aloud/i });
await user.click(button);
expect(mockSynthesize).toHaveBeenCalledWith("Hello", {
voice: "alloy",
tier: "premium",
});
});
});
describe("loading state", () => {
it("should show loading indicator while synthesizing", () => {
mockUseTextToSpeech.mockReturnValue({
synthesize: mockSynthesize,
play: mockPlay,
pause: mockPause,
stop: mockStop,
audioUrl: null,
isLoading: true,
error: null,
isPlaying: false,
duration: 0,
currentTime: 0,
});
render(<TextToSpeechButton text="Hello world" />);
const button = screen.getByRole("button", { name: /synthesizing/i });
expect(button).toBeInTheDocument();
expect(button).toBeDisabled();
});
});
describe("audio player integration", () => {
it("should show AudioPlayer when audio is available", () => {
mockUseTextToSpeech.mockReturnValue({
synthesize: mockSynthesize,
play: mockPlay,
pause: mockPause,
stop: mockStop,
audioUrl: "blob:mock-url",
isLoading: false,
error: null,
isPlaying: false,
duration: 30,
currentTime: 0,
});
render(<TextToSpeechButton text="Hello world" />);
expect(screen.getByRole("region", { name: /audio player/i })).toBeInTheDocument();
});
});
describe("error state", () => {
it("should display error message when synthesis fails", () => {
mockUseTextToSpeech.mockReturnValue({
synthesize: mockSynthesize,
play: mockPlay,
pause: mockPause,
stop: mockStop,
audioUrl: null,
isLoading: false,
error: "Synthesis failed",
isPlaying: false,
duration: 0,
currentTime: 0,
});
render(<TextToSpeechButton text="Hello world" />);
expect(screen.getByText(/synthesis failed/i)).toBeInTheDocument();
});
});
describe("accessibility", () => {
it("should have proper aria label on button", () => {
render(<TextToSpeechButton text="Hello world" />);
const button = screen.getByRole("button", { name: /read aloud/i });
expect(button).toBeInTheDocument();
});
});
describe("design", () => {
it("should not use aggressive colors", () => {
const { container } = render(<TextToSpeechButton text="Hello world" />);
const allElements = container.querySelectorAll("*");
allElements.forEach((el) => {
const className = el.className;
if (typeof className === "string") {
expect(className).not.toMatch(/bg-red-|text-red-|border-red-/);
}
});
});
});
});

View File

@@ -0,0 +1,126 @@
/**
* TextToSpeechButton Component
* "Read aloud" button that synthesizes text and plays it via AudioPlayer.
*
* Accepts text as a prop, with optional voice and tier selection.
* Shows loading state during synthesis and integrates AudioPlayer for playback.
*
* Follows PDA-friendly design: no aggressive colors, calm interface.
*/
import { useCallback } from "react";
import type { ReactElement } from "react";
import { useTextToSpeech } from "@/hooks/useTextToSpeech";
import type { SynthesizeOptions } from "@/hooks/useTextToSpeech";
import { AudioPlayer } from "./AudioPlayer";
export interface TextToSpeechButtonProps {
/** The text to synthesize to speech */
text: string;
/** Optional voice ID to use */
voice?: string;
/** Optional tier (e.g. "standard", "premium") */
tier?: string;
/** Optional className for the container */
className?: string;
}
/**
* TextToSpeechButton provides a "Read aloud" button that synthesizes
* the given text and displays an AudioPlayer for playback control.
*/
export function TextToSpeechButton({
text,
voice,
tier,
className = "",
}: TextToSpeechButtonProps): ReactElement {
const { synthesize, audioUrl, isLoading, error } = useTextToSpeech();
/**
* Handle read aloud button click
*/
const handleClick = useCallback(async (): Promise<void> => {
let options: SynthesizeOptions | undefined;
if (voice !== undefined || tier !== undefined) {
options = {};
if (voice !== undefined) options.voice = voice;
if (tier !== undefined) options.tier = tier;
}
await synthesize(text, options);
}, [text, voice, tier, synthesize]);
return (
<div className={`flex flex-col gap-2 ${className}`}>
{/* Read Aloud Button */}
<button
type="button"
onClick={() => void handleClick()}
disabled={isLoading}
aria-label={isLoading ? "Synthesizing speech" : "Read aloud"}
className="inline-flex items-center gap-2 rounded-lg border border-gray-200 bg-white px-3 py-1.5 text-sm font-medium text-gray-700 transition-colors hover:bg-gray-50 focus:outline-none focus:ring-2 focus:ring-blue-300 disabled:cursor-not-allowed disabled:opacity-50"
>
{isLoading ? (
<>
{/* Spinner */}
<svg
className="h-4 w-4 animate-spin text-gray-500"
viewBox="0 0 24 24"
fill="none"
aria-hidden="true"
>
<circle
cx="12"
cy="12"
r="10"
stroke="currentColor"
strokeWidth="3"
className="opacity-25"
/>
<path
fill="currentColor"
d="M4 12a8 8 0 018-8V0C5.373 0 0 5.373 0 12h4z"
className="opacity-75"
/>
</svg>
<span>Synthesizing...</span>
</>
) : (
<>
{/* Speaker Icon */}
<svg
width="16"
height="16"
viewBox="0 0 24 24"
fill="none"
stroke="currentColor"
strokeWidth="2"
strokeLinecap="round"
strokeLinejoin="round"
aria-hidden="true"
>
<polygon points="11 5 6 9 2 9 2 15 6 15 11 19 11 5" />
<path d="M15.54 8.46a5 5 0 010 7.07" />
<path d="M19.07 4.93a10 10 0 010 14.14" />
</svg>
<span>Read aloud</span>
</>
)}
</button>
{/* Error Display */}
{error && (
<p className="text-sm text-amber-600" role="alert">
{error}
</p>
)}
{/* Audio Player (shown after synthesis) */}
{audioUrl && <AudioPlayer src={audioUrl} />}
</div>
);
}
export default TextToSpeechButton;

View File

@@ -0,0 +1,228 @@
import { describe, it, expect, vi, beforeEach } from "vitest";
import { render, screen } from "@testing-library/react";
import userEvent from "@testing-library/user-event";
import { VoiceInput } from "./VoiceInput";
// Mock the useVoiceInput hook
const mockStartRecording = vi.fn();
const mockStopRecording = vi.fn();
vi.mock("@/hooks/useVoiceInput", () => ({
useVoiceInput: vi.fn(() => ({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: null,
audioLevel: 0,
})),
}));
// We need to import after mocking
import { useVoiceInput } from "@/hooks/useVoiceInput";
describe("VoiceInput", (): void => {
beforeEach((): void => {
vi.clearAllMocks();
// Reset mock implementation to default
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: null,
audioLevel: 0,
});
});
it("should render a microphone button", (): void => {
render(<VoiceInput />);
const button = screen.getByRole("button", {
name: /start voice input/i,
});
expect(button).toBeInTheDocument();
});
it("should have accessible aria label", (): void => {
render(<VoiceInput />);
const button = screen.getByRole("button", {
name: /start voice input/i,
});
expect(button).toHaveAttribute("aria-label", "Start voice input");
});
it("should call startRecording when mic button is clicked", async (): Promise<void> => {
const user = userEvent.setup();
render(<VoiceInput />);
const button = screen.getByRole("button", {
name: /start voice input/i,
});
await user.click(button);
expect(mockStartRecording).toHaveBeenCalledTimes(1);
});
it("should show recording state when isRecording is true", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: true,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: null,
audioLevel: 0.5,
});
render(<VoiceInput />);
const button = screen.getByRole("button", {
name: /stop voice input/i,
});
expect(button).toBeInTheDocument();
});
it("should call stopRecording when mic button is clicked while recording", async (): Promise<void> => {
const user = userEvent.setup();
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: true,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: null,
audioLevel: 0.5,
});
render(<VoiceInput />);
const button = screen.getByRole("button", {
name: /stop voice input/i,
});
await user.click(button);
expect(mockStopRecording).toHaveBeenCalledTimes(1);
});
it("should display partial transcription text", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: true,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "hello worl",
error: null,
audioLevel: 0.3,
});
render(<VoiceInput />);
expect(screen.getByText("hello worl")).toBeInTheDocument();
});
it("should display final transcript text", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "hello world",
partialTranscript: "",
error: null,
audioLevel: 0,
});
render(<VoiceInput />);
expect(screen.getByText("hello world")).toBeInTheDocument();
});
it("should display error message", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: "Microphone access not available",
audioLevel: 0,
});
render(<VoiceInput />);
expect(screen.getByText("Microphone access not available")).toBeInTheDocument();
});
it("should call onTranscript callback prop", (): void => {
const onTranscript = vi.fn();
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "final text",
partialTranscript: "",
error: null,
audioLevel: 0,
});
render(<VoiceInput onTranscript={onTranscript} />);
// The onTranscript prop is passed to the hook - we verify the prop is accepted
expect(useVoiceInput).toHaveBeenCalledWith(
expect.objectContaining({
onTranscript,
})
);
});
it("should use calm, non-aggressive design for recording indicator", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: true,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: null,
audioLevel: 0.5,
});
render(<VoiceInput />);
// Check there are no aggressive red colors in the recording state
const button = screen.getByRole("button", { name: /stop voice input/i });
const className = button.className;
expect(className).not.toMatch(/bg-red-|text-red-|border-red-/);
});
it("should use calm design for error display", (): void => {
vi.mocked(useVoiceInput).mockReturnValue({
isRecording: false,
startRecording: mockStartRecording,
stopRecording: mockStopRecording,
transcript: "",
partialTranscript: "",
error: "Something went wrong",
audioLevel: 0,
});
render(<VoiceInput />);
const errorEl = screen.getByText("Something went wrong");
const className = errorEl.className;
expect(className).not.toMatch(/text-red-600|bg-red-/);
});
it("should be disabled when disabled prop is true", (): void => {
render(<VoiceInput disabled />);
const button = screen.getByRole("button", {
name: /start voice input/i,
});
expect(button).toBeDisabled();
});
});

View File

@@ -0,0 +1,146 @@
/**
* VoiceInput component
*
* Provides a microphone button with visual feedback for voice input.
* Click to start/stop recording with real-time transcription display.
*
* Design principles:
* - PDA-friendly: calm, non-aggressive colors
* - Gentle pulsing animation for recording state (blue/green)
* - Mobile-friendly touch interaction
* - Accessible with proper aria labels
*/
import { useVoiceInput } from "@/hooks/useVoiceInput";
import type { UseVoiceInputOptions } from "@/hooks/useVoiceInput";
import { AudioVisualizer } from "./AudioVisualizer";
import { Mic, MicOff } from "lucide-react";
export interface VoiceInputProps {
/** Callback fired when final transcription is received */
onTranscript?: (text: string) => void;
/** Whether to use WebSocket streaming (default: true) */
useWebSocket?: boolean;
/** Whether the input is disabled */
disabled?: boolean;
/** Additional CSS classes for the container */
className?: string;
}
/**
* Voice input component with microphone capture and real-time transcription.
* Shows a mic button that toggles recording, with visual feedback
* and transcription text display.
*/
export function VoiceInput({
onTranscript,
useWebSocket: useWs,
disabled = false,
className = "",
}: VoiceInputProps): React.JSX.Element {
const hookOptions: UseVoiceInputOptions = {};
if (onTranscript !== undefined) {
hookOptions.onTranscript = onTranscript;
}
if (useWs !== undefined) {
hookOptions.useWebSocket = useWs;
}
const {
isRecording,
startRecording,
stopRecording,
transcript,
partialTranscript,
error,
audioLevel,
} = useVoiceInput(hookOptions);
const handleClick = (): void => {
if (isRecording) {
stopRecording();
} else {
void startRecording();
}
};
const displayText = isRecording ? partialTranscript : transcript;
return (
<div className={`flex flex-col items-center gap-3 ${className}`}>
{/* Mic button with recording indicator */}
<div className="relative flex items-center gap-2">
{/* Pulsing ring animation when recording */}
{isRecording && (
<div
className="absolute inset-0 -m-1 rounded-full bg-sky-400/20 animate-pulse"
aria-hidden="true"
/>
)}
<button
type="button"
onClick={handleClick}
disabled={disabled}
aria-label={isRecording ? "Stop voice input" : "Start voice input"}
className={`
relative z-10 flex items-center justify-center
w-10 h-10 rounded-full transition-all duration-200
focus:outline-none focus:ring-2 focus:ring-sky-400 focus:ring-offset-2
disabled:opacity-50 disabled:cursor-not-allowed
${
isRecording
? "bg-sky-500 text-white hover:bg-sky-600 shadow-md"
: "bg-slate-100 text-slate-600 hover:bg-slate-200 dark:bg-slate-700 dark:text-slate-300 dark:hover:bg-slate-600"
}
`}
>
{isRecording ? (
<MicOff className="w-5 h-5" aria-hidden="true" />
) : (
<Mic className="w-5 h-5" aria-hidden="true" />
)}
</button>
{/* Audio level visualizer - shown during recording */}
{isRecording && (
<AudioVisualizer audioLevel={audioLevel} isActive={isRecording} barCount={5} />
)}
</div>
{/* Recording status indicator */}
{isRecording && (
<div className="flex items-center gap-1.5 text-xs text-sky-600 dark:text-sky-400">
<span className="w-2 h-2 rounded-full bg-sky-500 animate-pulse" aria-hidden="true" />
<span>Listening...</span>
</div>
)}
{/* Transcription text display */}
{displayText && (
<p
className={`
text-sm max-w-md text-center px-3 py-1.5 rounded-lg
${
isRecording
? "text-slate-500 dark:text-slate-400 bg-slate-50 dark:bg-slate-800/50 italic"
: "text-slate-700 dark:text-slate-200 bg-slate-100 dark:bg-slate-800"
}
`}
>
{displayText}
</p>
)}
{/* Error display - calm, non-aggressive */}
{error && (
<p
className="text-sm text-amber-700 dark:text-amber-400 bg-amber-50 dark:bg-amber-900/20 px-3 py-1.5 rounded-lg max-w-md text-center"
role="alert"
>
{error}
</p>
)}
</div>
);
}

View File

@@ -0,0 +1,8 @@
export { VoiceInput } from "./VoiceInput";
export type { VoiceInputProps } from "./VoiceInput";
export { AudioVisualizer } from "./AudioVisualizer";
export type { AudioVisualizerProps } from "./AudioVisualizer";
export { AudioPlayer } from "./AudioPlayer";
export type { AudioPlayerProps } from "./AudioPlayer";
export { TextToSpeechButton } from "./TextToSpeechButton";
export type { TextToSpeechButtonProps } from "./TextToSpeechButton";