Overview

Convert text to natural-sounding speech with a single API call

Introduction

The Speechify API converts text into lifelike audio. Send text, get back audio — in MP3, OGG, AAC, WAV, or raw PCM.

Python

TypeScript

cURL

1 from speechify import Speechify
2 
3 client = Speechify()  # uses SPEECHIFY_API_KEY env var
4 
5 response = client.tts.audio.speech(
6     input="Welcome to Speechify!",
7     voice_id="george",
8     audio_format="mp3",
9 )
10 
11 with open("output.mp3", "wb") as f:
12     f.write(response.audio_data)

What you can do

Feature	Description
Text to Speech	Convert up to 2,000 characters per request
Streaming	Stream audio for up to 20,000 characters
Voice Cloning	Clone any voice from a 10-30 second sample
Emotion Control	Add emotions like cheerful, sad, angry to speech
50+ Languages	Full support for 6 languages, 17 in beta, 26 coming soon
SSML	Fine-grained control over pitch, rate, pauses, and emphasis

SDKs

Python

pip install speechify-api

TypeScript

npm install @speechify/api

REST API

Direct HTTP calls

Resources

Quickstart — Make your first API call in 5 minutes
API Reference — Full endpoint documentation
Examples Repository — End-to-end demo projects

1	from speechify import Speechify
2
3	client = Speechify() # uses SPEECHIFY_API_KEY env var
4
5	response = client.tts.audio.speech(
6	input="Welcome to Speechify!",
7	voice_id="george",
8	audio_format="mp3",
9	)
10
11	with open("output.mp3", "wb") as f:
12	f.write(response.audio_data)