ElevenLabs Hello World

Overview

Generate speech from text using the ElevenLabs TTS API. This skill covers the core

POST /v1/text-to-speech/{voice_id}

Prerequisites

• Completed

  elevenlabs-install-auth

  setup
• Valid API key in

  ELEVENLABS_API_KEY

Instructions

Step 1: Text-to-Speech with the SDK

TypeScript (recommended):

import { ElevenLabsClient } from "@elevenlabs/elevenlabs-js";
import { createWriteStream } from "fs";
import { Readable } from "stream";
import { pipeline } from "stream/promises";

const client = new ElevenLabsClient();

async function generateSpeech() {
  // Use a pre-made voice — "Rachel" is a default voice available on all accounts
  // Find voice IDs via: GET /v1/voices
  const audio = await client.textToSpeech.convert("21m00Tcm4TlvDq8ikWAM", {
    text: "Hello! This is your first ElevenLabs text-to-speech generation.",
    model_id: "eleven_multilingual_v2",  // Best quality, 29 languages
    voice_settings: {
      stability: 0.5,           // 0-1: lower = more expressive
      similarity_boost: 0.75,   // 0-1: higher = closer to original voice
      style: 0.0,               // 0-1: higher = more dramatic (costs more latency)
      speed: 1.0,               // 0.7-1.2: speech speed multiplier
    },
  });

  // audio is a ReadableStream — pipe to file
  await pipeline(
    Readable.fromWeb(audio as any),
    createWriteStream("output.mp3")
  );

  console.log("Audio saved to output.mp3");
}

generateSpeech().catch(console.error);

Python:

from elevenlabs.client import ElevenLabsClient

client = ElevenLabsClient()

audio = client.text_to_speech.convert(
    voice_id="21m00Tcm4TlvDq8ikWAM",  # Rachel
    text="Hello! This is your first ElevenLabs text-to-speech generation.",
    model_id="eleven_multilingual_v2",
    voice_settings={
        "stability": 0.5,
        "similarity_boost": 0.75,
        "style": 0.0,
    },
)

with open("output.mp3", "wb") as f:
    for chunk in audio:
        f.write(chunk)

print("Audio saved to output.mp3")

Step 2: Using cURL (Raw REST API)

curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/21m00Tcm4TlvDq8ikWAM" \
  -H "xi-api-key: ${ELEVENLABS_API_KEY}" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello from the ElevenLabs API!",
    "model_id": "eleven_multilingual_v2",
    "voice_settings": {
      "stability": 0.5,
      "similarity_boost": 0.75
    }
  }' \
  --output output.mp3

Step 3: Streaming TTS (Low Latency)

For real-time playback, use the streaming endpoint:

async function streamSpeech() {
  const audioStream = await client.textToSpeech.stream("21m00Tcm4TlvDq8ikWAM", {
    text: "This audio is streamed in real-time for low-latency playback.",
    model_id: "eleven_flash_v2_5",  // Optimized for streaming (~75ms latency)
    output_format: "mp3_22050_32",  // codec_sampleRate_bitrate
  });

  // Stream chunks arrive as they're generated
  const writer = createWriteStream("streamed.mp3");
  for await (const chunk of audioStream) {
    writer.write(chunk);
  }
  writer.end();
  console.log("Streamed audio saved to streamed.mp3");
}

Available Models

eleven_v3

eleven_multilingual_v2

eleven_flash_v2_5

eleven_turbo_v2_5

eleven_monolingual_v1

Common Default Voice IDs

21m00Tcm4TlvDq8ikWAM

AZnzlk1XvdvUeBnXmlld

EXAVITQu4vr4xnSDxMaL

ErXwobaYiN019PkySvjV

TxGEqnHWrfWFTfGW9XjX

Output Formats

Specified as

codec_sampleRate_bitrate

• mp3_44100_128

  (default, high quality)

• mp3_22050_32

  (smaller file, streaming)

• pcm_16000

  (raw PCM for processing)

• pcm_44100

  (high-quality raw)

• ulaw_8000

  (telephony)

Error Handling

voice_not_found

GET /v1/voices

invalid_api_key

ELEVENLABS_API_KEY

model_not_found

text_too_long

quota_exceeded

Resources

• TTS API Reference
• Stream API Reference
• Models Overview
• Voice Library

Next Steps

Proceed to

elevenlabs-local-dev-loop

elevenlabs-core-workflow-a