# Create a Meditation App with AI-Generated Voice > Source: > Published: 2026-10-06 07:08:36+00:00 If you’ve ever built a simple chatbot or a notification system, you’ve already worked with APIs, authentication, and the occasional rate limit. Adding a *real‑time, natural‑sounding voice* turns a text‑based experience into something that feels comforting, personal, and almost therapeutic. For meditation, that’s a game‑changer: a gentle narrator can guide breathing, set intentions, or play ambient sounds—all while keeping your users engaged. In this post we’ll walk through: By the end, you’ll have a working prototype that you can extend into a full‑featured meditation app. Text‑to‑speech (TTS) is a mature field, but most free or open‑source solutions lag behind commercial providers in naturalness, voice variety, and developer experience. ElevenLabs offers: If you’re looking for a quick, production‑ready voice solution, check out ElevenLabs at [https://try.elevenlabs.io/kr07zfuqn1bp](https://try.elevenlabs.io/kr07zfuqn1bp). The free tier is generous, and you can upgrade to a paid plan for higher quality and more requests. A generic “calm” voice can work, but a cloned voice that mimics the user’s own voice or a brand‑specific narrator creates a deeper connection. ElevenLabs’ cloning workflow is simple: `voice_id`. Below is a quick Python script to upload a clip and get the `voice_id`: ``` python import os import requests API_KEY = os.getenv("ELEVENLABS_API_KEY") UPLOAD_URL = "https://api.elevenlabs.io/v1/voices" headers = {"xi-api-key": API_KEY, "Accept": "application/json"} # 1️⃣ Record a short sample (e.g., 30s) and save as `sample.wav` with open("sample.wav", "rb") as audio: files = {"file": ("sample.wav", audio, "audio/wav")} response = requests.post(f"{UPLOAD_URL}/clone", headers=headers, files=files) if response.ok: voice_id = response.json()["voice_id"] print("Your cloned voice ID:", voice_id) else: print("Error:", response.text) ``` Remember to keep the audio file under 3 MB for the free tier. If you need larger samples, upgrade your plan. Once you have a `voice_id`, you can use it in subsequent synthesis calls to produce a voice that *sounds* like the original speaker. A typical meditation routine might consist of: We’ll generate these on demand using ElevenLabs’ `synthesize` endpoint. ``` python import os import requests API_KEY = os.getenv("ELEVENLABS_API_KEY") VOICE_ID = os.getenv("VOICE_ID") # The cloned voice ID you got earlier TTS_URL = f"https://api.elevenlabs.io/v1/text-to-speech/{VOICE_ID}" headers = { "xi-api-key": API_KEY, "Content-Type": "application/json" } def synthesize(text, output_path="output.mp3"): payload = { "text": text, "voice_settings": { "stability": 0.5, # 0-1.0 "similarity_boost": 0.75 } } response = requests.post(TTS_URL, headers=headers, json=payload, stream=True) if response.status_code == 200: with open(output_path, "wb") as f: for chunk in response.iter_content(chunk_size=8192): f.write(chunk) print(f"Saved audio to {output_path}") else: print("Synthesis failed:", response.text) # Demo: a short guided breathing session script = """ Welcome. Let's take a moment to settle in. Close your eyes, and breathe in slowly through your nose. Hold for a count of three. Now exhale gently through your mouth. Repeat this cycle for a few minutes. """ synthesize(script) ``` This script pulls the voice model from ElevenLabs and writes the resulting MP3 to disk. You can adapt the `synthesize` function to stream audio directly to a mobile app or a web player. `curl` for Quick Tests If you prefer the CLI: ``` curl -X POST "https://api.elevenlabs.io/v1/text-to-speech/$VOICE_ID" \ -H "xi-api-key: $ELEVENLABS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "text": "Hello from ElevenLabs! This is a test of the TTS engine.", "voice_settings": { "stability": 0.5, "similarity_boost": 0.75 } }' --output test.mp3 ``` Let’s assume you’re building a React Native app. The simplest way to play synthesized audio is to: `expo-av` or `react-native-sound`. Here’s a quick React Native snippet: ``` python import React, { useEffect } from 'react'; import { View, Button } from 'react-native'; import { Audio } from 'expo-av'; export default function MeditationScreen() { const playAudio = async () => { const { sound } = await Audio.Sound.createAsync( { uri: 'https://your-backend.com/audio/meditation.mp3' }, { shouldPlay: true } ); // Optionally unload when finished sound.setOnPlaybackStatusUpdate((status) => { if (status.didJustFinish) { sound.unloadAsync(); } }); }; return (