Ai music generator

Photo Credit: Technivation Meta has released its own AI music generator called ‘MusicGen,’ trained on 10,000 licensed music tracks. The AI music generator works much like Google’s MusicLM, generating a snippet of about 12 seconds of audio based on a text prompt. I experimented with MusicLM’s model upon its initial release and discovered it’s pretty great at generating electronic music and synthwave, but not much else. MusicGen wants to be better at a wide variety of genres. MusicGen was trained on 20,000 hours of music that includes 10,000 “high-quality” license tracks and 390,000 instrument-only tracks from ShutterStock and Pond5. While the model itself is open source, Meta has not provided the code it used to train the model. Instead, pre-trained models are available for download. The results from both MusicGen and Prompting an acceptable piece of audio from a text-to-audio AI means understanding how to describe what you want to hear. Simple prompts like ‘ambient chiptune music’ are so open-ended that simply re-feeding the prompt to the music generator will generate wildly different songs after each generation. Meanwhile, a prompt like “Slow tempo, bass-and-drums-led reggae song. Sustained electric guitar. High-pitched bongos with ringing tones. Vocals are relaxed with a laid-back feel, very expressive,” will help the language model build something that sounds very similar after each successful generation. As generative AI progresses, these language models will become be...

Hot off the heels of the announcement of its new VR headset, the Quest 3 (and an impressive display at the Meta Games Showcase), Meta are popping back into the news cycle once again after its Audiocraft research team has released a free-to-all, open source, Meta AI text-to-music language model, MusicGen. MusicGen works similarly to how other multi-modal Large Language Models (LLMs) like ChatGPT, DALL-E, and Midjourney, using AI to translate natural language prompts into a desired result – in this case, music. Meta MusicGen: the best text-to-audio LLM MusicGen isn’t the first of its kind. In fact, Google recently unveiled a similar tool of its own by the name of MusicLM. However, while not the first, MusicGen is seemingly a little further along than the Alphabet group’s efforts with researchers finding MusicGen to best it across a number of categories. Researchers compared Meta’s MusicGen with similar software including Google’s MusicLM, Riffusion, Mousai, and Noise2Music. The study found that both objective and subjective measurements saw Noise2Music able to deliver a more “plausible” result, but MusicGen scored highest for accurate musical concepts, audio-to-text alignment, and human-scored overall audio quality and accuracy. That being said, Meta hasn’t provided the data it was train on (which is reportedly ~20,000 hours of licensed music, including an internal datasheet of 10,000 high-quality tracks and samples from both Shutterstock and Pond5), but has provided pre-tra...

memorable end-of-year wrap-up for Yotta's users. In two weeks, Uberduck helped Yotta create and ship 150,000 professionally produced rap songs with lyric videos, every one customized to each individual user. Yotta's users loved their raps and shared them across social media, driving hundreds of new checking accounts.

While other MediaPost newsletters and articles remain free to all ... our new Research Intelligencer service is reserved for paid subscribers ... Subscribe today to gain access to every Research Intelligencer article we publish as well as the exclusive daily newsletter, full access to The MediaPost Cases, first-look research and daily insights from Joe Mandese, Editor in Chief. advertisement To increase the program's speed, Meta used its 32Khz EnCodec audio tokenizer to generate small bits of music that can be processed in parallel. The generator can also be “steered” with existing songs, creating a new clip with both description and reference audio. MusicGen is open-source, setting it apart from Google’s MusicLM, and can be used to generate commercial music or anything else. Meta is not imposing restrictions on how the program can be used, stating that the music MusicGen was trained on is “covered by legal agreements with the right holders.”

Google has been working on MusicLM for a while but has only just made it available to regular folks. Much like other generative AI – such as It can create music with a range of instruments and even vocals – though don’t expect actual words from the AI singers. Instead, the vocals come out as noises that give you a flavor of the tune rather than a complete full-on song. (Image credit: Google) The AI does have a few other limitations. For one, it’s not overly accurate and the tracks MusicLM creates feel a little generic – though this is a fault we’ve found with pretty much every generative AI; when it’s merely amalgamating music it’s previously heard you can’t expect it to create something unique, nor to understand why the music invokes certain emotions. For another, the AI won’t produce music based on another artist. So you could ask it for a hip-hop or western track, but not something in the style of Lil Nas X or Taylor Swift. If you try asking for something in the style of an artist you’ll get an error message asking you to provide a different prompt. That said, this would be seen as a positive by many artists rather than a negative of MusicLM. (Image credit: Google) Start by heading to the To sign up hit the “Register your interest” button and you’ll be taken to a short survey where you’re asked to provide details about where you’re from and why you want to join the Test Kitchen. At the end of the survey, if you aren’t signed in already, you’ll need to log in to your Goo...

Photo Credit: Technivation Meta has released its own AI music generator called ‘MusicGen,’ trained on 10,000 licensed music tracks. The AI music generator works much like Google’s MusicLM, generating a snippet of about 12 seconds of audio based on a text prompt. I experimented with MusicLM’s model upon its initial release and discovered it’s pretty great at generating electronic music and synthwave, but not much else. MusicGen wants to be better at a wide variety of genres. MusicGen was trained on 20,000 hours of music that includes 10,000 “high-quality” license tracks and 390,000 instrument-only tracks from ShutterStock and Pond5. While the model itself is open source, Meta has not provided the code it used to train the model. Instead, pre-trained models are available for download. The results from both MusicGen and Prompting an acceptable piece of audio from a text-to-audio AI means understanding how to describe what you want to hear. Simple prompts like ‘ambient chiptune music’ are so open-ended that simply re-feeding the prompt to the music generator will generate wildly different songs after each generation. Meanwhile, a prompt like “Slow tempo, bass-and-drums-led reggae song. Sustained electric guitar. High-pitched bongos with ringing tones. Vocals are relaxed with a laid-back feel, very expressive,” will help the language model build something that sounds very similar after each successful generation. As generative AI progresses, these language models will become be...

Hot off the heels of the announcement of its new VR headset, the Quest 3 (and an impressive display at the Meta Games Showcase), Meta are popping back into the news cycle once again after its Audiocraft research team has released a free-to-all, open source, Meta AI text-to-music language model, MusicGen. MusicGen works similarly to how other multi-modal Large Language Models (LLMs) like ChatGPT, DALL-E, and Midjourney, using AI to translate natural language prompts into a desired result – in this case, music. Meta MusicGen: the best text-to-audio LLM MusicGen isn’t the first of its kind. In fact, Google recently unveiled a similar tool of its own by the name of MusicLM. However, while not the first, MusicGen is seemingly a little further along than the Alphabet group’s efforts with researchers finding MusicGen to best it across a number of categories. Researchers compared Meta’s MusicGen with similar software including Google’s MusicLM, Riffusion, Mousai, and Noise2Music. The study found that both objective and subjective measurements saw Noise2Music able to deliver a more “plausible” result, but MusicGen scored highest for accurate musical concepts, audio-to-text alignment, and human-scored overall audio quality and accuracy. That being said, Meta hasn’t provided the data it was train on (which is reportedly ~20,000 hours of licensed music, including an internal datasheet of 10,000 high-quality tracks and samples from both Shutterstock and Pond5), but has provided pre-tra...

memorable end-of-year wrap-up for Yotta's users. In two weeks, Uberduck helped Yotta create and ship 150,000 professionally produced rap songs with lyric videos, every one customized to each individual user. Yotta's users loved their raps and shared them across social media, driving hundreds of new checking accounts.

Google has been working on MusicLM for a while but has only just made it available to regular folks. Much like other generative AI – such as It can create music with a range of instruments and even vocals – though don’t expect actual words from the AI singers. Instead, the vocals come out as noises that give you a flavor of the tune rather than a complete full-on song. (Image credit: Google) The AI does have a few other limitations. For one, it’s not overly accurate and the tracks MusicLM creates feel a little generic – though this is a fault we’ve found with pretty much every generative AI; when it’s merely amalgamating music it’s previously heard you can’t expect it to create something unique, nor to understand why the music invokes certain emotions. For another, the AI won’t produce music based on another artist. So you could ask it for a hip-hop or western track, but not something in the style of Lil Nas X or Taylor Swift. If you try asking for something in the style of an artist you’ll get an error message asking you to provide a different prompt. That said, this would be seen as a positive by many artists rather than a negative of MusicLM. (Image credit: Google) Start by heading to the To sign up hit the “Register your interest” button and you’ll be taken to a short survey where you’re asked to provide details about where you’re from and why you want to join the Test Kitchen. At the end of the survey, if you aren’t signed in already, you’ll need to log in to your Goo...

While other MediaPost newsletters and articles remain free to all ... our new Research Intelligencer service is reserved for paid subscribers ... Subscribe today to gain access to every Research Intelligencer article we publish as well as the exclusive daily newsletter, full access to The MediaPost Cases, first-look research and daily insights from Joe Mandese, Editor in Chief. advertisement To increase the program's speed, Meta used its 32Khz EnCodec audio tokenizer to generate small bits of music that can be processed in parallel. The generator can also be “steered” with existing songs, creating a new clip with both description and reference audio. MusicGen is open-source, setting it apart from Google’s MusicLM, and can be used to generate commercial music or anything else. Meta is not imposing restrictions on how the program can be used, stating that the music MusicGen was trained on is “covered by legal agreements with the right holders.”