Official SDKs

Python

$
pip install speechify-api

1
from speechify import Speechify
2
3
client = Speechify()  # uses SPEECHIFY_API_KEY env var
4
5
response = client.tts.audio.speech(
6
    input="Hello from the Python SDK!",
7
    voice_id="george",
8
    audio_format="mp3",
9
)

• Requires Python 3.8+
• Source code & docs
• PyPI package

TypeScript / JavaScript

$
npm install @speechify/api

1
import { SpeechifyClient } from "@speechify/api";
2
3
const client = new SpeechifyClient();  // uses SPEECHIFY_API_KEY env var
4
5
const response = await client.tts.audio.speech({
6
    input: "Hello from the TypeScript SDK!",
7
    voiceId: "george",
8
    audioFormat: "mp3",
9
});

• Works in Node.js and modern browsers
• Source code & docs
• NPM package

REST API

No SDK needed — make direct HTTP calls from any language:

$
curl -X POST https://api.speechify.ai/v1/audio/speech \
>
  -H "Authorization: Bearer $SPEECHIFY_API_KEY" \
>
  -H "Content-Type: application/json" \
>
  -d '{
>
    "input": "Hello from the REST API!",
>
    "voice_id": "george",
>
    "audio_format": "mp3"
>
  }'

See the API Reference for all available endpoints.

Environment variables

Both SDKs read the SPEECHIFY_API_KEY environment variable automatically:

$
export SPEECHIFY_API_KEY="your-api-key-here"

You can also pass the key explicitly when creating the client. See the Authentication guide for security best practices.