Ethical AI Music Production with Udio and Kits.ai

In this video, the creator demonstrates the use of AI in music production by first composing an original song in Udio and then utilizing Kits AI to modify vocals and harmonies. The video showcases the new desktop app from Kits and its voice conversion capabilities, emphasizing the ethical sourcing of AI voices. The host trains a voice model using their own vocal samples and blends it with existing models to create unique vocal tracks. The process involves adjusting pitch, experimenting with different voice models, and applying effects to achieve a desired sound. The video also discusses the importance of using AI as a tool for creative inspiration rather than a replacement for human musicians. It concludes by encouraging viewers to explore AI music tools for practical applications in their creative process.

Takeaways

• 🎵 The video demonstrates how to create an original song in Udio and then use Kits AI to modify vocals and harmonies.
• 🌟 Kits AI has a new desktop app and updates to its website, offering more tools for voice conversion.
• 📚 Kits AI voices are sourced ethically, and the company has a clear philosophy on the ethical use of AI in music production.
• 🎙️ Users can train their own voice models using Kits AI with specific types of audio, such as dry vocals without effects or background music.
• 🔄 The ability to blend different voice models to create unique voice combinations is available within Kits AI.
• 🚫 The video emphasizes the importance of avoiding copyright restrictions when using AI music generation tools.
• 🎶 AI-generated music can inspire creativity rather than replacing human musicians, and live performances will always hold a unique value.
• 📈 AI music tools are not just for creating perfect songs but also for filling in creative gaps, such as when a musician needs a specific voice type that they don't have access to.
• 🔧 The video shows the process of using an external audio editor to further refine the AI-generated music and vocals.
• 🔄 The process includes experimenting with different voice models and effects to find the best fit for the song.
• ⚙️ Future videos will explore additional software that can convert audio tracks into MIDI tracks, allowing for further manipulation of notes and harmonies.

Q & A

What is the main purpose of using Udio and Kits.ai in the context of the video?

The main purpose is to create an original song in Udio and then use Kits.ai to modify and add vocals and harmonies, demonstrating a workflow for using these music generators as a source of creative inspiration.

What is the new feature available on Kits.ai that is mentioned in the transcript?

Kits.ai now has a desktop app available, which allows users to convert a voice into another voice without needing to be on their website.

How are the AI voices sourced in Kits.ai?

The AI voices in Kits.ai are sourced ethically, and the platform provides information on their ethical sourcing and philosophy on using AI for music production.

What is the process of training a voice model in Kits.ai?

To train a voice model, you need to upload dry vocal samples, ideally without effects, background music, or harmonies. The process involves uploading a maximum of 60 minutes of such vocal data for the AI to learn and create a voice model.

What is the role of the vocal remover and stem splitter tools in Kits.ai?

The vocal remover tool is used to separate vocals from the instrumentals in a track, while the stem splitter can divide the instrumentals into different components like drums and bass. These tools help in obtaining clean vocal or instrumental samples for further processing or training voice models.

How can users create unique voice models in Kits.ai?

Users can blend existing models from Kits.ai's voice library or mix them with their trained models to create completely unique voice models by adjusting the ratio between the selected models.

What is the significance of creating an original song in Udio before using Kits.ai?

Creating an original song in Udio ensures that there are no copyright restrictions when using Kits.ai to modify the song. It also provides a base track that can be creatively transformed using the various features of Kits.ai.

How does the speaker view the impact of AI on the music industry and live musicians?

The speaker believes that AI is not a threat to live musicians or the music industry. Live performances and the nuances they bring are irreplaceable, and AI can be seen as a tool to inspire new creativity rather than a replacement for human musicians.

What are some of the post-production techniques mentioned for refining the vocals in the audio editor?

The speaker mentions using simple Studio Reverb, EQ adjustments, and a compressor to refine the vocals. Additionally, they discuss panning vocals to different sides of the spectrum and using time and pitch shifters to create harmonies.

What is the final output format of the song created in Udio?

The final output format of the song created in Udio is an MP3 file, which can be easily imported into an external audio editor for further processing.

How does the speaker suggest using AI music generation tools in a creative process?

The speaker suggests using AI music generation tools to fill in creative or inspirational blanks, such as when a musician needs a specific type of voice or instrument that they do not have access to. It's about enhancing creativity and not necessarily creating a perfect, publish-ready song.

What advice does the speaker give to musicians who are skeptical about AI in music?

The speaker encourages skeptical musicians to see the practical uses of AI in studios, emphasizing that AI can be a valuable tool for creativity and inspiration rather than a replacement for human creativity.

Outlines

00:00

🎼 Introduction to Kits AI for Creative Music Inspiration

The video begins with an introduction to the use of Kits AI for music generation. The host outlines the plan to create an original song, then utilize Kits AI to modify vocals and harmonies, emphasizing the tool's role as a source of creative inspiration. The host also discusses the new desktop app from Kits and its features, including voice conversion and the ethical sourcing of AI voices. The process of training a voice model with Kits AI is explained, highlighting the need for clear, dry vocals without effects or background music.

05:01

🎤 Creating a Song and Modifying Vocals with Kits AI

The host demonstrates creating a song in udio, opting for a specific style and manually crafting lyrics due to the limitations of AI-generated lyrics. The song created is about the host's vocal orange cat. The video then shows how to extend the song and download it, followed by separating vocals from the instrumentals using Kits AI. The host guides viewers through converting the original male vocal track to a female voice using Kits AI, adjusting pitch levels, and experimenting with different voice models to find the best fit for the song.

10:03

🔄 Exploring Voice Conversion and Adding Effects

The video continues with experimenting with different voice models in Kits AI to find a suitable replacement for the original male voice. The host discusses the limitations of pitch conversion and the process of downloading and implementing the converted vocals into an audio editing software. Effects such as reverb and EQ are added, and the host emphasizes the importance of balancing the frequencies of different vocal tracks to avoid a muddied mix.

15:05

🎵 Blending Vocals and Creating Harmony

The host explores blending different vocal models to create unique sounds and enhance the song's harmony. The process involves adding a custom voice model based on the host's speaking voice, adjusting pitch, and aligning the tracks to create a cohesive mix. The video also touches on the potential of using AI to generate harmonies and the idea of using additional software to convert audio tracks into MIDI for further manipulation.

20:07

🛠️ Final Touches and Creative Editing

The video concludes with final editing and mixing techniques. The host discusses the possibility of adding real instruments and using AI as a creative starting point rather than a perfect end product. The focus is on using AI ethically and creatively to overcome limitations such as the lack of available singers or instruments. The host also hints at future videos that will explore software that can convert audio tracks to MIDI for more in-depth music creation.

25:07

🌟 Embracing AI in Music Creation

In the final paragraph, the host summarizes the purpose of using AI in music creation, encouraging musicians to see AI as a tool for inspiration and creativity rather than a replacement for human artistry. The host dispels concerns about AI replacing musicians and invites viewers to engage with the content by subscribing and commenting on what aspects they'd like to learn more about. The video ends on a playful note, reminding viewers of the fun and creative potential of AI in music.

Keywords

💡Udio

Udio is an online platform for music creation that allows users to generate songs by specifying a style or genre. In the video, it is used to create an original song which is then modified using Kits AI, demonstrating how these tools can be used for creative inspiration rather than creating a final, publishable product.

💡Kits AI

Kits AI is a voice conversion tool that can be used to change and add vocals to a song. It offers a range of AI voices and also allows users to train their own voice models. The tool is highlighted in the video for its ethical sourcing of voice data and its potential for creative use in music production.

💡AI Voices

AI Voices refer to the synthesized vocal sounds created by AI technology. Kits AI provides over 35 AI voices, which can be used for various purposes such as creating AI covers or adding singers to a project. The video emphasizes the ethical considerations regarding the use of AI voices, particularly concerning copyright and data sourcing.

💡Voice Training

Voice training in the context of the video involves uploading a sample of a voice to Kits AI, which then 'learns' from this sample to replicate or convert the voice. The process requires clear, dry vocals without effects or background music. The video demonstrates how the host trained their own voice model using speaking samples.

💡Ethical AI

Ethical AI refers to the responsible and moral use of artificial intelligence, particularly concerning data sourcing and representation. Kits AI is noted for sourcing its voice data ethically, which is important for addressing copyright concerns and ensuring the respectful use of individuals' voices in AI applications.

💡Vocal Removal

Vocal removal is a process where the vocal track is separated from the instrumental part of a song. Kits AI has a feature that attempts to remove vocals from a mixed audio file, which is useful for those looking to isolate instrumentals or create new vocal versions of existing tracks.

💡Multitrack Session

A multitrack session is a method of recording and mixing where different elements of a song are recorded on separate tracks. This allows for greater control and flexibility during the editing and mixing process. In the video, Adobe Audition is used to create a multitrack session where the original song and modified vocals are edited.

💡Audio Effects

Audio effects are processes or algorithms applied to an audio signal to alter its sound. In the video, effects such as reverb, compression, and pitch shifting are used to enhance the vocals and create a fuller, more polished sound. The host discusses adding these effects in post-production after the AI voice conversion.

💡Harmonies

Harmonies are additional vocal parts that are sung along with the main melody to create a richer, more complex sound. The video explores the idea of adding harmonies to the song using AI, which can help flesh out a song and provide a more complete sound, especially when real singers are not available.

💡Music Generation

Music generation refers to the process of creating music using software or AI algorithms. The video discusses the use of music generators like Udio and Kits AI not to replace human musicians but to inspire creativity and provide tools to help musicians, particularly in situations where they may lack certain resources, like access to singers or instruments.

💡Creative Inspiration

Creative inspiration is the stimulation of new ideas, concepts, or solutions and is often sought by artists and musicians. The video emphasizes that tools like Udio and Kits AI should be used as sources of creative inspiration rather than as a means to produce perfect, finished songs. They can help musicians overcome creative blocks or fill in gaps where traditional resources are lacking.

Highlights

Today's session involves creating an original song in Udio and using Kits AI to modify vocals and harmonies.

Kits AI has released a new desktop app, offering more convenience for users.

Kits AI is a voice conversion tool that can be used for AI covers or adding singers to a project.

Kits AI provides over 35 AI voices and ensures ethical sourcing of these voices.

The process of training a voice model in Kits AI is straightforward but requires specific types of audio.

Users can blend different voice models in Kits AI to create unique vocal sounds.

The presenter discusses the importance of ethical use of AI in music production and addresses copyright concerns.

AI music generators like Udio are used as creative inspiration rather than a replacement for human musicians.

The presenter emphasizes the value of live music performances and their irreplaceable nuances.

Udio is used to create a base song, which will be further modified using Kits AI.

The presenter manually writes lyrics for the song, finding AI-generated lyrics to be lacking in creativity.

Udio's song creation process is demonstrated, including extending the song and generating an outro.

The presenter extracts vocals from the Udio-generated song for further editing.

Adobe Audition is used as the audio editor to create variations of the vocal track.

Different vocal models are tested for the lead and backing vocals, adjusting pitch as needed.

The presenter discusses the limitations and creative potential of using AI-generated voices in music.

Harmony tracks are added to the song using AI conversion of a manually sung harmony.

The presenter suggests future videos will explore software that converts audio tracks into MIDI for further manipulation.

The final song is a demonstration of using AI as a tool for creativity and inspiration rather than a perfect production.

The session concludes with an encouragement for musicians to experiment with AI tools in a practical and ethical manner.