How to select a recommended voice for your Audio Asset

Choosing the right voice for your project can take time. By using the /voice/select endpoint, you can request a list of the five most suitable voices for your script, based on a provided ScriptID or content.

Code Example

import audiostack
import os

audiostack.api_key = os.environ['AUDIOSTACK_API_KEY']

advert = (
    "AudioStack's enterprise-grade audio AI technology seamlessly integrates into your product "
    "or workflow and cuts your production cycles to seconds while making your budgets go further. "
    "To find out more about all the cool things you can create using AudioStack, check out our workflow "
    "guides which you can find in the documentation at docs dot audiostack dot com"
)

print("Creating your script from text...")
script = audiostack.Content.Script.create(scriptText=advert)

print("Finding the most relevant voice recommendations...")
req = audiostack.Speech.Voice.select_for_script(scriptId=script.data["scriptId"])


for i in req.data["voices"]:
    print(f'{i["alias"]} is the perfect narrator for your script!')
    print(f"Generating speech for {i['alias']}")
    speech = audiostack.Speech.TTS.create(scriptItem=script, voice=i["alias"])

    print("Creating your audio asset...")
    mix = audiostack.Production.Mix.create(speechItem=speech, soundTemplate="pulsing_guitar", masteringPreset="balanced")

    print("Downloading your MP3")
    encoder = audiostack.Delivery.Encoder.encode_mix(productionItem=mix, preset="mp3")
    encoder.download(fileName=f"{script.scriptName}__{i['alias']}.mp3", path=".")