AUDIO

Web-based Text To Speech Tools:

1. Natural Reader
   naturalreaders.com
   • Free and easy to use with natural-sounding voices.
2. Voice Dream Reader (Mobile)
   iOS & Android
   • Highly customizable with great voice quality.

Browser Extensions:

1. Read Aloud (Chrome/Edge/Firefox)
   • Adds a “read aloud” feature to your browser, useful for websites and online documents.

Built-in Device Features:

1. Mac & iPhone/iPad:
   Go to Settings > Accessibility > Spoken Content and turn on “Speak Screen.”
2. Android:
   Use the Select to Speak feature under Accessibility settings.
3. Windows:
   Use the built-in Narrator or the Read Aloud feature in Microsoft Edge.

Text to Audio tools:

1. AIVA (Artificial Intelligence Virtual Artist)

Best for: Composing classical and cinematic music

• AIVA generates music in different genres and can be used for film scoring, video games, and personal projects.
• You can customize key, tempo, and mood, and even edit the generated compositions manually.
  Website: aiva.ai

2. Amper Music

Best for: Quick music creation for media and background tracks

• Amper allows users to create royalty-free music by selecting a genre, style, and mood.
• Great for non-musicians looking to generate professional background music.
  Website: ampermusic.com

3. Soundraw

Best for: Customizable music loops

• Offers a wide range of moods, genres, and instruments.
• You can tweak the generated music by adjusting energy levels, length, and instruments in real-time.
  Website: soundraw.io

4. OpenAI’s MuseNet

Best for: AI-composed multi-instrumental tracks

• MuseNet can generate complex compositions with up to 10 instruments in various styles (jazz, pop, classical, etc.).
• It’s designed to understand intricate musical structures, making it ideal for experimentation.

5. Boomy

Best for: Creating and monetizing music

• You can generate songs in different genres (lo-fi, EDM, rap, etc.) and upload them to streaming services like Spotify and YouTube.
  Website: boomy.com

6. Ecrett Music

Best for: Royalty-free soundtracks for video creators

• Select a scene (e.g., travel, relaxation), a mood, and instruments to generate music suited for specific video content.
  Website: ecrettmusic.com

7. Google’s Magenta Studio

Best for: Experimental music creation

• A set of open-source tools for creating music using machine learning models.
• Great for users who are comfortable with DAWs and want to explore generative music.
  Website: magenta.tensorflow.org/studio

8. Beatoven.ai

Best for: Background music for podcasts and videos

• Choose from various genres and moods to create soundtracks that match your content perfectly.
  Website: beatoven.ai

9. Jukebox by OpenAI

Best for: Raw and experimental AI-generated songs with lyrics

• Jukebox generates music with vocals and lyrics in different styles. It’s great for advanced users experimenting with AI-generated audio.
  GitHub: Jukebox

10. YUE.ai

Best for: Raw and experimental AI-generated songs with lyrics

• Open-Source AI Music Generator
• Generate professional quality music with vocals from your lyrics using advanced AI technology. Create unlimited songs in various styles and languages.

Example

Prompt:
dark goth industrial song with deep male vocals and low frequency rhythms

Lyrics:

[Verse 1]
In the neon haze, where shadows dance,
We met beneath the siren’s trance.
Vinyl spins, the echoes call,
A heartbeat lost in the underground hall.

[Pre-Chorus]
Leather and lace, a requiem sigh,
We swore we’d never say goodbye.
Ripped-up dreams, in black we stand,
Side by side, hand in hand.

[Chorus]
We are forever in black, bound by the sound,
Through the static and noise, we’ll never back down.
Rhythms of midnight, electric and bold,
We’ll change the world with the stories we’ve told.

[Verse 2]
Silver chains and velvet nights,
Words unspoken in pale moonlight.
Every song a whispered vow,
No turning back, not then, not now.

[Pre-Chorus]
Leather and lace, a requiem sigh,
We swore we’d never say goodbye.
Ripped-up dreams, in black we stand,
Side by side, hand in hand.

[Chorus]
We are forever in black, bound by the sound,
Through the static and noise, we’ll never back down.
Rhythms of midnight, electric and bold,
We’ll change the world with the stories we’ve told.

[Bridge] (Whispered, distorted vocals)
The bassline pulses, the drumbeats crave,
In music’s arms, we are saved.
Ink on skin, scars on souls,
Together we burn, together we glow.

[Outro] (Haunting, ethereal fade-out)
No regrets, no goodbyes,
Just the music in our eyes.
We are forever in black…
Forever in black…

Result:

ACE STUDIO: AI Singing Voice Generator
https://acestudio.ai

https://www.youtube.com/@ACE-Studio

ASSIGNMENT

11 • Using any AI audio tool of your choice you will create a piece of music that integrates some form of human voice / speech / song. The piece must be beteen 1 and 3 minutes. Provide any prompts and screenshots of the creative process, and upload the finished MP3 / WAV / AIFF version to your DropBox folders. Be ready to play your song in class.