Transform Text intoHuman-Like SpeechInstantly

Add life to your applications, videos, and creative projects using high-quality AI voices. Get started in seconds with our OpenAI-compatible TTS API or online studio.

No Credit Card Required1,000 Free Characters Daily
Time to first token: 0 ms

Lightning Fast

Experience instant voice generation with our high-performance model that delivers results in milliseconds.

Natural Voices

Choose from 10+ high-quality voices with natural intonation and emotion.

Developer Friendly

OpenAI-compatible API with comprehensive documentation and examples.

Ready to add voice to your application?

Get started with our API in minutes. No credit card required.

Trusted by Thousands of Developers Worldwide

ReadByEar helps developers easily deliver compelling audio content for apps, videos, and interactive experiences.

"The most natural-sounding TTS I've used. The API is simple and the voices are incredibly lifelike."

Developer
Alex Chen
Senior Developer @ Tech Co

"We switched from a larger provider to ReadByEar TTS and saw better quality with 3x cost savings."

Developer
Sarah Johnson
CTO @ StartupX

"The voice quality is exceptional. We use it for all our video content, and our viewers love it."

Developer
Michael Zhang
Content Creator

Quick Start Guide

Get started with our API in minutes using these code examples. No credit card required.

API Reference

Complete examples for integrating with our API

Library Integration

pip install openai
from openai import OpenAI

# Initialize the client with our API endpoint
client = OpenAI(
    base_url="http://216.249.100.66:13524/v1",
    api_key="free-trial"  # Get your API key at readbyear.com/dashboard
)

# Stream to file
with client.audio.speech.with_streaming_response.create(
    voice="af_bella+em_santa",  # Single voice or multiple voice combo
    input="Hello world!"
) as response:
    response.stream_to_file("output.mp3")

Native HTTP Request

pip install requests numpy sounddevice
import requests
import numpy as np
import sounddevice as sd
import wave
import os

# Initialize audio stream
sample_rate = 24000
stream = sd.OutputStream(
    samplerate=sample_rate,
    channels=1,
    dtype=np.int16,
    blocksize=1024,
    latency="low"
)
stream.start()

try:
    # Make the API request
    response = requests.post(
        "http://216.249.100.66:13524/v1/audio/speech",
        headers={
            "Authorization": "Bearer free-trial"  # Get your API key at readbyear.com/dashboard
        },
        json={
            "input": "Hello world!",
            "voice": "af_bella",      # Single voice or combined voices: "em_santa+em_alex"
            "response_format": "pcm",  # Use PCM for streaming
            "stream": True,           # Enable streaming
            "lang_code": "e"          # Language code: e (English), s (Spanish), etc.
        },
        stream=True
    )
    response.raise_for_status()

    # Process the streaming response
    for chunk in response.iter_content(chunk_size=1024):
        audio_chunk = np.frombuffer(chunk, dtype=np.int16)
        stream.write(audio_chunk)     # Play audio in real-time

except requests.RequestException as e:
    print(f"Error making request: {e}")
finally:
    # Clean up
    stream.stop()
    stream.close()

Simple, Transparent Pricing

Start for free, upgrade when you need more. Pay only for what you use.