Turn your agent’s text into speech

The problem

A text agent produces words, not an audio waveform. It cannot choose a speaker’s voice or render pronunciation and timing by returning more text. A spoken interface needs a speech engine after the agent has decided what to say.

How NativePort helps

NativePort connects the agent’s script to ElevenLabs and returns playable audio. Choose a voice, send the text, and use the result in your app or save it as a file. There is no separate speech-provider account to wire into this flow.

Technical implementation

Use Python 3 with requests installed (python -m pip install requests). Set NATIVEPORT_API_KEY in your environment to your NativePort key. Run the snippets on your server, where your key stays private.

Choose a voice with GET /elevenlabs/v1/voices and set VOICE_ID.

python

import os
import requests

BASE = "https://api.nativeport.ai"
HEADERS = {"Authorization": f"Bearer {os.environ['NATIVEPORT_API_KEY']}"}

response = requests.post(
    BASE + "/elevenlabs/v1/text-to-speech/" + os.environ["VOICE_ID"],
    headers=HEADERS,
    json={"text": "Your order is ready for collection.",
          "model_id": "eleven_multilingual_v2"},
    timeout=120,
)
response.raise_for_status()
with open("reply.mp3", "wb") as audio:
    audio.write(response.content)

The response contains audio bytes, so save it as binary rather than trying to parse JSON. Play reply.mp3 in your app. For an interactive experience, the /elevenlabs/v1/text-to-speech/{voice_id}/stream route delivers audio as it is generated. See the ElevenLabs gateway reference.

Tool costs

Tool used in the example	Price per call
ElevenLabs — text to speech	$0.026375 / call

Prices in USD. Usage-based tools have no fixed per-call price. View pricing.

Let your agent build it

You don’t need to write this code yourself. Copy this page’s link and paste it into your agent. Ask it to follow the guide and implement the feature for you.

https://nativeport.ai/use-cases/text-to-speech/

The problem

How NativePort helps

Technical implementation

Tool costs

Let your agent build it

Keep exploring

Add spoken replies to Telegram and Discord bots

Analyze sentiment and review spoken content

Let your agent read spoken messages

Explore all use cases