Add sound design to text to speech

A common use case you might have is to add a sound design or soundbed to text to speech.

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 Design

Why is this different to background music

A backing track is often used to make up a sound design, but a sound design (sometimes called a soundbed) is more complicated.

Productions typically use these five sound design elements:

• Ambiance is the background noise that sets a scene. It should be appropriate and informative without overwhelming the recording’s focus.
• Foley sounds are the sounds of actions that make scenes seem more real. Ex: footstep sounds or material moving as someone walks
• Audio effects are 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.

Show me an example

Let's take this step by step.

Create text to speech with one of our 600 voices

Select a sound template from our Sound library

Add that sound template using our AI enhanced mixing and mastering engine

import audiostack
import os

audiostack.api_key = "APIKEY" # fill up

script = """

<as:section name="main" soundsegment="main">
 Are you ready to explore the vibrant city of Barcelona? Do you want to experience the culture, the nightlife, and the beauty of this incredible city? 
 Then we've got just the thing for you! 
 Join our travel agency for an unforgettable trip to Barcelona. Experience the bustling city streets, the stunning canals, and the charming architecture that Amsterdam is known for. Get lost in the vibrant nightlife, 
 explore the world-renowned museums, or simply soak in the local culture.
</as:section>


"""



names = ["Wren",  "jollie", "aspen"]
presets = ["musicenhanced", "balanced", "voiceenhanced"]
templates = ["your_take_30", "future_focus_30"]



script = audiostack.Content.Script.create(scriptText=script, scriptName="test", projectName="mastering_test")        

for name in names:
    # Creates text to speech
    speech = audiostack.Speech.TTS.create(
            scriptItem=script,
            voice=name,
            speed=100
    )
    for template in templates:

        for preset in presets:

            mix = audiostack.Production.Mix.create(
                speechItem=speech,
                soundTemplate=template,
                masteringPreset=preset,
            )
            print(mix)

      

            mix.download(fileName=f"V4_{name}_{template}_{preset}")

            print(mix)

Here we cycle through a few names, presets (notice how musicenhanced, balanced and voiceenhanced) sound differently and some different templates.

📘

If you want to upload your own sound templates

If you want to upload your own sound templates please reach out to [email protected] and we'll work on these things.