elevenlabs-core-workflow-b

# ElevenLabs Core Workflow B — Speech-to-Speech, Sound Effects & Audio Isolation ## Overview Secondary ElevenLabs workflows beyond TTS: (1) Speech-to-Speech voice conversion, (2) Sound Effects generation from text descriptions, (3) Audio Isolation for noise removal, and (4) Speech-to-Text transcription. ## Prerequisites - Completed `elevenlabs-install-auth` setup - For STS: source audio file in MP3/WAV/M4A format - For audio isolation: noisy audio file to clean ## Instructions ### Step 1: Speech-to-Speech (Voice Changer) Transform audio from one voice to another using `POST /v1/speech-to-speech/{voice_id}`: ```typescript import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js"; import { createReadStream, createWriteStream } from "fs"; import { Readable } from "stream"; import { pipeline } from "stream/promises"; const client = new ElevenLabsClient(); async function speechToSpeech( sourceAudioPath: string, targetVoiceId: string, outputPath: string ) { const audio = await client.speechToSpeech.convert(targetVoiceId, { audio: createReadStream(sourceAudioPath), model_id: "eleven_english_sts_v2", // STS-specific model voice_settings: JSON.stringify({ stability: 0.5, similarity_boost: 0.8, style: 0.0, }), remove_background_noise: true, // Built-in noise removal }); await pipeline(Readable.fromWeb(audio as any), createWriteStream(outputPath)); console.log(`Voice-converted audio saved to ${outputPath}`); } // Conve...