elevenlabs-core-workflow-b

name	elevenlabs-core-workflow-b
description	Implement ElevenLabs speech-to-speech, sound effects, audio isolation, and speech-to-text. Use when converting voice to another voice, generating sound effects from text, removing background noise, or transcribing audio. Trigger: "elevenlabs speech to speech", "voice changer", "sound effects", "audio isolation", "remove background noise", "elevenlabs transcribe".
allowed-tools	Read, Write, Edit, Bash(npm:*), Bash(curl:*), Grep
version	1.0.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","voice","ai","elevenlabs","speech-to-speech","sound-effects","audio-isolation"]
compatible-with	claude-code

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}:

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
    : .({
      : ,
      : ,
      : ,
    }),
    : ,  
  });

   (.(audio  ), (outputPath));
  .();
}


 (
  ,
  ,
  
);