JayPanoz/PlaybackAPI-Types-Interfaces.ts

## PlaybackAPI-Types-Interfaces.ts
interface Voice {
  id: string;           // Unique identifier
  name: string;         // Display name
  language: string;     // BCP 47 language tag
}

interface SpeechContent {
  text: string;        // Text or SSML content
  ssml?: boolean;      // If true, text contains SSML
}

type PlaybackState = "playing" | "paused" | "idle" | "loading" | "ready";

type PlaybackEvent =
  | "start"
  | "pause"
  | "resume"
  | "end"
  | "error"
  | "boundary"
  | "mark"
  | "idle"
  | "loading"
  | "ready";

interface PlaybackEngine {
  // Queue Management
  loadUtterances(contents: SpeechContent[]): void;

  // Voice config
  setRate(rate: number): void;
  setPitch(pitch: number): void;
  setVolume(volume: number): void;

  speak(utteranceIndex?: number): void;

  // State
  getState(): PlaybackState;

  // Events
  on(
    event: PlaybackEvent,
    callback: (...args: any[]) => void
  ): () => void;

  // Cleanup
  destroy(): Promise<void>;
}

interface EngineProvider {
  // Voice Management
  getVoices(): Promise<Voice[]>;

  // Engine Creation
  createEngine(voice: Voice): Promise<PlaybackEngine>;

  // Lifecycle
  destroy(): Promise<void>;
}

interface PlaybackNavigator {
  // TBD
  // Playback controls + events: play(idx?), pause, resume, stop
  // navigation + events: next, previous, jumpTo(idx)
  // readiumSpeech-prefixed events?
}

## Requirements.md

      
    Raw
  

              Requirements.md
            
          
    Playback API - Requirements

This document outlines the requirements for the Playback API, which provides a unified interface for controlling text-to-speech (TTS) playback.
1.1 Playback Control


Start, pause, resume, and stop
Handle both individual and batched text/SSML input
Report current playback state (playing, paused, stopped)

1.2 Text Processing


Accept plain text and SSML input
Support multiple utterances

1.3 Event System


Emit events for state changes
Provide word/sentence boundary information
Report errors and warnings

1.4 Voice Management


Select from available voices
Configure voice parameters (rate, pitch, volume)

Design

[WIP]
A PlaybackEngineProvider allows you to get available voices and create instances of the PlaybackEngine using one specific voice, language, etc.
This PlaybackEngine is using a voice, its parameters can be set, is loaded with utterances, can preload with context, and allows you to speak an utterance index.
A PlaybackNavigator then handles navigation, continuous play, etc.
	interface Voice {
	id: string; // Unique identifier
	name: string; // Display name
	language: string; // BCP 47 language tag
	}

	interface SpeechContent {
	text: string; // Text or SSML content
	ssml?: boolean; // If true, text contains SSML
	}

	type PlaybackState = "playing" \| "paused" \| "idle" \| "loading" \| "ready";

	type PlaybackEvent =
	\| "start"
	\| "pause"
	\| "resume"
	\| "end"
	\| "error"
	\| "boundary"
	\| "mark"
	\| "idle"
	\| "loading"
	\| "ready";

	interface PlaybackEngine {
	// Queue Management
	loadUtterances(contents: SpeechContent[]): void;

	// Voice config
	setRate(rate: number): void;
	setPitch(pitch: number): void;
	setVolume(volume: number): void;

	speak(utteranceIndex?: number): void;

	// State
	getState(): PlaybackState;

	// Events
	on(
	event: PlaybackEvent,
	callback: (...args: any[]) => void
	): () => void;

	// Cleanup
	destroy(): Promise<void>;
	}

	interface EngineProvider {
	// Voice Management
	getVoices(): Promise<Voice[]>;

	// Engine Creation
	createEngine(voice: Voice): Promise<PlaybackEngine>;

	// Lifecycle
	destroy(): Promise<void>;
	}

	interface PlaybackNavigator {
	// TBD
	// Playback controls + events: play(idx?), pause, resume, stop
	// navigation + events: next, previous, jumpTo(idx)
	// readiumSpeech-prefixed events?
	}
No results found