Sound Design

One major benefit of AudioStack is that you can easily combine generated speech with sound designs, including music from our sound template library, atmospheric sound effects, or with your own audio files.

What is a Sound Design

From Wikipedia:

Sound design is the art and practice of creating soundtracks for a variety of needs. It involves specifying, acquiring or creating auditory elements using audio production techniques and tools. It is employed in a variety of disciplines including filmmaking, television production, video game development, theatre, sound recording and reproduction, live performance, sound art, post-production, radio, new media and musical instrument development. Sound design commonly involves performing (see e.g. foley) and editing of previously composed or recorded audio, such as sound effects and dialogue for the purposes of the medium, but it can also involve creating sounds from scratch through synthesizers. A sound designer is one who practices sound design.

Sound Templates

How is Sound Design different from Backing Music?

A backing track is often used to make up a sound design, but a sound design (sometimes called a soundbed) can be more complicated. Sound designs can include a variety of different sound design elements to enhance your audio asset, such as:

• Ambience -- the background noise that sets a scene. It should be appropriate and informative without overwhelming the recording’s focus.
• Foley sounds -- the sounds of actions that make scenes seem more real. Ex: footstep sounds or material moving as someone walks
• Audio effects -- sounds created because they don’t exist in the real world. Ex: an alien invasion.
  A voice-over is the voice of a narrator who is either a character or an unseen narrator driving a story forward.
  Music includes songs and instrumental pieces that influence mood and help tell the story.

At AudioStack, sound design includes sound templates (which contain music, sometimes organised into different sections and adjustable in length) and atmospheric effects.

Code Example

Let's take this step by step.

1️⃣ Create text to speech with one of our 1300+ voices

2️⃣ Select a sound design from our list of sound templates - we've given you some recommendations in the example.

3️⃣ Add that sound template and produce your asset using our AI enhanced mixing and mastering engine

import audiostack
import os

audiostack.api_key = "APIKEY"  # fill in your API key!
SCRIPT_TEXT = """
<as:section name="main" soundsegment="main">
Sound designs can enhance your generated speech by adding sound effects, ambience and backing music to bring your audio to life.
</as:section>
"""

# Define voice names, presets, and templates for audio production
names = ["Elaine", "Edward"]
presets = ["musicenhanced", "balanced", "voiceenhanced"]
templates = ["friendly_electronica", "eighties_chill", "funky_summer"]

# Create a script instance in Audiostack
script = audiostack.Content.Script.create(
    scriptText=SCRIPT_TEXT, 
    scriptName="test", 
    projectName="sound_template_tests"
)

# Loop through names, templates, and presets to generate and download mixes
for name in names:
    # Generate text-to-speech for each name
    speech = audiostack.Speech.TTS.create(
        scriptItem=script, 
        voice=name
    )

    for template in templates:
        for preset in presets:
            # Create a mix with the specified template and preset
            mix = audiostack.Production.Mix.create(
                speechItem=speech, 
                soundTemplate=template, 
                masteringPreset=preset
            )

            # Download and save the mix file with a formatted name
            mix.download(fileName=f"{name}_{template}_{preset}")

            # Optional: print mix details (can be commented out if not needed)
            print(mix)

Here we cycle through a few different voice options, mastering presets and templates. You can find out more about mixing and mastering here.