The speech API and streaming and your first script

The concept

The platform offers a speech API that returns audio for a piece of text, and a streaming endpoint for live audio, which is how narration gets into an application rather than a download folder. The idea is simple: the same model you have been chatting with also answers a web request, so you can put it inside a script, a spreadsheet or a page. A key identifies you; a request sends the text; a response comes back as data.

The reason to try it once, even if you never build anything: it makes the chat version less mysterious. You see that the whole conversation is text in and text out, that your instructions are literally lines of a request, and that "the model" is one parameter among several.

A first call looks like this:

import requests

VOICE = "YOUR_VOICE_ID"
KEY   = "YOUR_ELEVENLABS_KEY"

text = "This is a test of the narration pipeline. It should sound like a person."

r = requests.post(
    f"https://api.elevenlabs.io/v1/text-to-speech/{VOICE}",
    headers={"xi-api-key": KEY, "Content-Type": "application/json"},
    json={"text": text, "model_id": "eleven_multilingual_v2"},
)

open("narration.mp3", "wb").write(r.content)