Ethical AI Music Production with Udio and Kits.ai

Bob Doyle Media
18 Apr 202426:36

TLDRIn 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 and enhance vocals and harmonies. The process showcases a workflow for ethical AI music generation, emphasizing the importance of using these tools as a source of creative inspiration rather than a replacement for human musicianship. The video highlights the ethical sourcing of AI voices, the ability to train custom voice models, and the blending of models to create unique vocal styles. The creator also discusses the limitations and potential of AI in music, encouraging viewers to embrace these tools for their creative potential and not to worry about AI replacing human musicians. The video concludes with a demonstration of how AI can be used to fill gaps in the creative process, such as adding harmonies or fleshing out demo tracks, and the potential for further exploration and customization with additional software.

Takeaways

  • 🎵 The video demonstrates creating an original song in Udio and then using Kits AI to modify vocals and harmonies, showcasing a workflow for music generation tools.
  • 🌟 Kits AI has released a desktop app, offering the ability to convert a voice into another voice that the user has created or is included with Kits AI.
  • 📚 Kits AI voices are sourced ethically, and the company has a clear philosophy on the ethical use of AI in music production, which is detailed on their website.
  • 🎙️ Users can train their own voice models with Kits AI using clear, dry vocal samples without effects or background music for the best results.
  • 🔄 The process of blending voice models allows for the creation of unique voice models by mixing different samples or a user's trained model with those available in Kits AI's library.
  • 🚫 The video emphasizes the importance of avoiding copyright restrictions when using music generation tools and suggests creating original content as a starting point.
  • 🎶 The host shares their personal experience with training a voice model based on speaking rather than singing, noting the nuances in vocal performance that may be lost without singing samples.
  • 🔊 Kits AI provides tools for post-production adjustments, such as a vocal remover and stem splitter, to refine the audio before training or conversion.
  • 🛠️ The video discusses the use of external audio editors, like Adobe Audition, for further audio processing and creating a multitrack session to build the final song.
  • ⚙️ The process of converting vocals involves selecting a voice model, adjusting pitch levels, and applying effects to integrate the AI-generated vocals into the song.
  • 🎧 The final song is a combination of AI-generated vocals, manually adjusted audio tracks, and the user's own creativity, highlighting the potential of AI as a tool for musical inspiration and collaboration.

Q & A

  • What is the main focus of the video?

    -The video focuses on creating an original song using Udio and then enhancing it with vocals and harmonies using Kits AI, demonstrating a workflow for using these music generators as creative inspiration.

  • What is the significance of using AI voices in music production?

    -AI voices offer a wide range of options for musicians, allowing them to add vocals or create covers without the need for live singers. They also provide a tool for ethical music production, respecting copyright and the originality of artists' voices.

  • How does Kits AI ensure the ethical sourcing of its AI voices?

    -Kits AI sources its voices ethically, and more information on their process and philosophy can be found through the provided link in the video description.

  • What is the process of training a voice model with Kits AI?

    -To train a voice model, one needs to upload dry vocal samples, ideally without effects, background music, or harmonies. The process requires clear voice samples, which can be of speaking or singing, depending on the desired outcome.

  • How can users blend different voice models in Kits AI?

    -Users can blend different voice models by selecting models from Kits AI's library or using their trained model and then deciding the ratio between the selected models to create a completely new and unique voice.

  • What is the role of Udio in the music creation process demonstrated in the video?

    -Udio is used to create the original song structure, including the music and a base vocal track. The platform allows for the customization of song styles and the writing of original lyrics.

  • How does the video presenter approach the creation of original lyrics?

    -The presenter chooses to write their own lyrics for specificity and personal relevance, as they find the lyric writing capability of AI services to be somewhat limited in creativity.

  • What is the purpose of using the vocal remover and stem splitter tools in Kits AI?

    -The vocal remover and stem splitter tools are used to isolate and separate different elements of a track, such as vocals from instrumentals or individual instrumental parts, to allow for more precise editing and mixing.

  • How does the video presenter modify the original male vocal track to fit a female vocal model?

    -The presenter converts the original male vocal track to a female model by using the conversion tool in Kits AI, adjusting the pitch level to match the original vocal range, and applying any necessary audio effects.

  • What are the presenter's thoughts on the potential impact of AI on live musicians?

    -The presenter believes that live musicians, especially those who perform for the love of music rather than money, have little to worry about from AI. They suggest that the nuances of live performances will always be appreciated and that AI is more of a tool for inspiring creativity.

  • How does the video presenter suggest using AI-generated music in the music industry?

    -The presenter suggests using AI-generated music as a base or inspiration for creativity, allowing musicians to add real instruments, change voices, or rework the track in various styles using other software. They emphasize the ethical and creative use of AI as a tool rather than a replacement for human musicians.

Outlines

00:00

🎼 Introduction to Kits AI and Music Creation

The video begins with an introduction to the use of Kits AI for music creation. The host explains that they will create an original song and then use Kits AI to modify vocals and harmonies, demonstrating the tool's capabilities as a source of creative inspiration. The host also discusses the new desktop app for Kits and the ethical sourcing of AI voices, emphasizing the importance of respecting copyright and the human element in music creation.

05:01

🎹 Creating a Song in udio and Editing with Kits AI

The host demonstrates how to create a song in udio, choosing a specific style and manually writing the lyrics for a more personalized touch. They then use the extend feature to generate additional sections of the song and download the audio. The process continues with the removal of backing vocals and reverb in preparation for further editing in an external audio editor. The host also explores blending different AI voice models to create a unique vocal sound.

10:03

🔄 Converting and Experimenting with Vocal Tracks

In this section, the host experiments with converting the original male vocal track to a female voice using Kits AI. They discuss the process of finding a suitable voice model that matches the pitch and style of the original track. The host also shares their experience with using their own trained voice model and the challenges of converting it for a backing vocal part. They highlight the potential for using AI-generated vocals as a creative tool rather than a replacement for human musicians.

15:05

🎛️ Audio Processing and Vocal Mixing

The host delves into the audio processing aspect by adding effects, equalization, and compression to the vocal tracks. They discuss the importance of panning and frequency adjustments to create a balanced mix. The video also covers the process of adding harmony to the vocals by recording a harmony track, converting it into an AI voice, and then integrating it back into the mix. The host emphasizes the experimental nature of the process and encourages viewers to embrace imperfections as part of the creative journey.

20:07

🎧 Final Touches and Creative Reflections

The host focuses on finalizing the song by making creative edits, adjusting the volume of different vocal tracks, and adding a chorus for a fuller sound. They reflect on the potential for real musicians to enhance the AI-generated base track and the ethical considerations of using AI in music production. The host concludes by encouraging viewers to use AI tools as a means to spark creativity and to explore the practical applications of AI in the music industry.

25:07

📚 Embracing AI in Music and Encouraging Further Exploration

In the concluding paragraph, the host summarizes the key points discussed in the video, including the practical use of AI in music production and the importance of using these tools ethically and creatively. They invite feedback from viewers and encourage further exploration of AI in music, emphasizing the potential for AI to inspire new creative ideas and collaborations in the music industry.

Mindmap

Keywords

💡Ethical AI

Ethical AI refers to the responsible and moral development and use of artificial intelligence. In the context of the video, ethical AI is crucial when sourcing voices for music production to ensure that data is obtained in a way that respects privacy and intellectual property rights. The video emphasizes the ethical sourcing of all AI voices used in Kits AI, aligning with the company's philosophy on ethical AI use in music production.

💡Udio

Udio is a music production platform that allows users to create original songs. In the video, the creator uses Udio to generate a song's instrumental and melody, which will later be modified with AI vocals. Udio is significant as it provides the foundation for the music that will be further developed with AI tools.

💡Kits AI

Kits AI is a voice conversion tool that can transform one voice into another, which is used in the video to alter and add vocals and harmonies to the song created in Udio. Kits AI is central to the video's demonstration of how AI can be used to inspire creativity in music production without infringing on copyright or ethical concerns.

💡Voice Conversion

Voice conversion is the process of changing one voice to sound like another. In the video, the host uses Kits AI for voice conversion to change the original male vocals of the song created in Udio to a female voice, showcasing the tool's capability to adapt vocals to different styles and genders.

💡AI Voices

AI voices are synthetic vocal models created using machine learning techniques. The video discusses the use of over 35 AI voices available in Kits AI, which can be used for various creative purposes, such as adding singers to a project or creating AI covers. These voices are ethically sourced and can be further customized by users.

💡Training a Voice Model

Training a voice model involves uploading a sample of a voice to an AI system so that it can learn and replicate the characteristics of that voice. In the video, the host mentions having trained their own voice model using Kits AI, which requires clear, dry vocals without effects or background music. This process is essential for creating personalized AI voices for music projects.

💡Vocal Remover

A vocal remover is a tool that attempts to isolate and remove the vocal track from a song's mix, leaving the instrumental parts behind. The video demonstrates the use of a vocal remover within Kits AI to separate vocals from the instrumentals of the song created in Udio, preparing it for further editing and the addition of AI vocals.

💡Stem Splitter

A stem splitter is a tool that separates a song's mix into its constituent parts, such as drums, bass, and other instruments. While not explicitly used in the video, the host mentions the existence of a stem splitter in Kits AI, which could be used for more detailed audio editing and production.

💡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 during the editing process. In the video, the host uses Adobe Audition to create a multitrack session for the song, enabling them to manipulate individual vocal and instrumental elements.

💡Harmonies

Harmonies are additional vocal parts that sing notes concurrently with the main melody, often at a different pitch to create a richer sound. The video discusses the potential for using AI to generate harmony tracks, which can then be converted into AI voices and added to the song, enhancing its depth and complexity.

💡Creative Inspiration

Creative inspiration refers to the stimulation of new ideas or solutions, often through the use of external tools or media. The video's main theme is using AI music generation tools like Udio and Kits AI as sources of creative inspiration rather than as replacements for human creativity. The host emphasizes that these tools should be used to fill in gaps or spark new ideas in the music creation process.

Highlights

The video demonstrates creating an original song in Udio and using Kits AI to modify vocals and harmonies.

Kits AI has released a new desktop app, offering voice conversion tools outside of the web browser.

Kits AI provides over 35 AI voices sourced ethically, addressing copyright concerns.

The process of training a voice model with Kits AI requires specific types of audio to ensure a clear voice sample.

Kits AI allows users to blend models to create unique voice models for their projects.

The video discusses the ethical sourcing of voice data for AI music production.

AI music generators are seen as a source of creative inspiration rather than a replacement for human musicians.

The presenter shares their personal experience with training a voice model based on their speaking voice.

Udio is used to create a song in the style of Dr. John, with the user providing their own lyrics.

The video shows how to extend a song in Udio and add an outro to create a complete piece.

Adobe Audition is used as the external audio editor to further process the vocals and instrumentals.

The presenter converts the original male vocal track to a female voice using Kits AI.

Different vocal effects and EQ adjustments are explored to enhance the final mix.

The video covers how to add multiple vocal tracks and harmonies to a song using AI voices.

The presenter discusses the limitations of AI in music production and the importance of human creativity.

AI music tools are positioned as a means to fill creative gaps, such as when live singers are unavailable.

The video concludes by encouraging musicians to use AI as a tool for inspiration and creativity in music production.