
音楽生成AI ・ 歌声生成AI ・ 音生成AI のリリース年表
主な「音楽生成AI」「歌声生成AI」「音生成AI」「音声認識AI」のリリース年表をまとめました。
2020年
2月22日 NEUTORINO
4月30日 OpenAI Jukebox
9月17日 SOUNDRAW
12月25日 Synthesizer V AI
2021年
1月29 AudioLDM
7月21日 suno
音楽生成・歌声生成
AI 🤝 Music
— Suno (@suno_ai_) July 21, 2023
Suno can now sing! Our new model generates music with vocals, and you can try it now on Diśčòrd. See below for some early examples and an invite link to our open beta: pic.twitter.com/CjjfYM2YRZ
8月2日 AudioCraft (MusicGen・AudioGen・EnCodec)
9月13日 Stable Audio
10月17日 ACE Studio
11月30日 Seamless Communication (SeamlessM4T v2・SeamlessExpressive・SeamlessStreaming・Seamless)
12月13日 MusicFX
2024年
1月3日 M2UGen
・M2UGen/M2UGen-MusicGen-small
・M2UGen/M2UGen-MusicGen-medium
・M2UGen/M2UGen-AudioLDM2
2月16日 MAGNeT
音楽生成・音生成
3月7日 data2vec 2.0・HuBERT・data2vec
3月8日 Sonauto
3月11日 OptimizerAI
Rolling out the web version and the high-performance v1 of OptimizerAI at the end of this month! 🚀 Eager to try text-to-sound right away? Come check it out on https://t.co/0FLwQl6Bx2 🎶✨ pic.twitter.com/e2jawnr6fH
— OptimizerAI (@OptimizerAI) March 10, 2024
3月22日 suno v3
V3 IS HERE 💥 We are excited to introduce our first model capable of producing radio-quality music. v3 allows you to make full, 2 minute songs in seconds and is now available to all users. Try it for free here: https://t.co/s2hNzxc87W
— Suno (@suno_ai_) March 21, 2024
Thank you to our Pro + Premier members; v3… pic.twitter.com/ZmRm8XnZcw
4月3日 Stable Audio 2.0
4月10日 udio
Introducing Udio, an app for music creation and sharing that allows you to generate amazing music in your favorite styles with intuitive and powerful text-prompting.
— udio (@udiomusic) April 10, 2024
1/11 pic.twitter.com/al5uYAsU5k
4月13日 musicgen-songstarter-v0.2
4月15日 OptimizerAI 1.0
Introducing OptimizerAI 1.0 - the best text-to-sound effect model.
— OptimizerAI (@OptimizerAI) April 15, 2024
Bring your games, videos, movies, and animations to life with AI sound effects!
Available on web and Discord. Get started now at https://t.co/IKDsDGoPeb pic.twitter.com/JJILhxHyWs
5月25日 suno v3.5
v4 is cooking 👩🍳 In the meantime, we are rolling out early access to v3.5, which is now available to Pro and Premier members!
— Suno (@suno_ai_) May 24, 2024
3.5 is an updated version of v3, with the following improvements:
• 4-minute max clip length. You can now get your full song in a single generation!…
5月31日 ElevenLabs - Sound Effects
Text to Sound Effects is here. Our newest AI Audio model generates sound effects, short instrumental tracks, soundscapes, and a wide variety of character voices, all from a text prompt. Available now for all users.
— ElevenLabs (@elevenlabsio) May 31, 2024
Everyone from content creators, video game developers, to film… pic.twitter.com/yHrh3C3qk5
6月5日 Stable Audio Open
6月17日 DeepMind - video-to-audio
6月19日 ElevenLabs - Text to Sound Effects API ・ Video to Sounds Effects app
We are excited to introduce the Text to Sound Effects API.
— ElevenLabs (@elevenlabsio) June 17, 2024
To showcase it - we've built the first Video to Sounds Effects app. This app is available for free online and fully open-source. pic.twitter.com/8aalo8GCSo
6月28日 FoleyCrafter
7月4日 ElevenLabs - TVoice Isolator
Introducing Voice Isolator.
— ElevenLabs (@elevenlabsio) July 3, 2024
Remove unwanted background noise and extract crystal clear dialogue from any audio to make your next podcast, interview, or film sound like it was recorded in the studio.
Try it free: https://t.co/lF4RTkhIxJ pic.twitter.com/GrJHuunLq4
12月10日 MMAudio
1月16日 Hailuo T2A-01-HD
🔊Find Your Dream Voice with Hailuo Audio HD: A New Era in Voice Synthesis!
— Hailuo AI (MiniMax) (@Hailuo_AI) January 15, 2025
MiniMax proudly unveils T2A-01-HD, the next breakthrough in Text-to-Audio technology. With unmatched versatility, emotional depth, and multilingual authenticity, this model redefines what’s possible in… pic.twitter.com/ouWbcwqXgG
1月28日 YuE
2月24日 Dream Machine - video-to-audio
Video to Audio is now here in #DreamMachine. To generate sound for your video generations, just select the new "Audio" button. Create with a single click or describe with prompts for more customized direction. Audio is available now in beta for free to all users. pic.twitter.com/DyHt8meeO8
— Luma AI (@LumaLabsAI) February 24, 2025
3月3日 DiffRhythm
4月9日 Lyria
4月9日 Amazon Nova Sonic
🗣️ Announcing Amazon Nova Sonic, a new speech-to-speech foundation model that can understand voice as input & generate a human-like voice as output.
— Amazon Science (@AmazonScience) April 8, 2025
➡️ Available via a new API in Amazon Bedrock, the model simplifies the development of voice applications: https://t.co/nbZQvrIFnF
5月1日 suno v4.5
v4.5 just dropped for Pro & Premier subscribers 🔥 A wider range of genres, richer vocals, & enhanced prompt understanding for songs that match your vision.
— Suno (@SunoMusic) May 1, 2025
What’s New:
🙌 Expanded genres & smarter mashups: More genre options — Blends like midwest emo + neosoul or EDM + folk… pic.twitter.com/MGp3zH8VHd
5月7日 ACE-Step
🎵 An open-source music generation model (ACE-Step) was just released by StepFun AI + ACE Studio!
— mrfakename (@realmrfakename) May 6, 2025
📐 3.5B parameter open-weight model
🔓 Apache-2.0 license
🎙️ Supports lyric generation
🚀 Can generate 4m songs in just 20s on A100 pic.twitter.com/re0duWVNYf
5月20日 Lyria 2
8月12日 Suno Studio
Suno Studio is coming...
— Suno (@SunoMusic) August 11, 2025
Multi-track creation.
Export to MIDI.
And much more.
Join the waitlist nowhttps://t.co/L0dlpcXSAg pic.twitter.com/EqbTvuo4lF
8月16日 Eleven Labs - Video-to-Music
Today, we’re launching a new Video-to-Music flow in ElevenLabs Studio.
— ElevenLabs (@elevenlabsio) August 15, 2025
In one click, our Eleven Music model generates a custom soundtrack based on your video’s context.
After adding music, you can layer in voiceovers and SFX directly in Studio.
More examples in thread. pic.twitter.com/HkMgeYZSvU
9月24日 Suno v5
Everything changes with Suno v5. Launching today for Pro and Premier subscribers, the world's best music model delivers more immersive audio, authentic vocals, and unparalleled creative control that will transform how you make music.
— Suno (@SunoMusic) September 23, 2025
This breakthrough goes beyond making better… pic.twitter.com/QNrci69JW2
12月16日 SAM Audio
2026年
1月15日 HeartMuLa
2月3日 ACE-Step v1.5
We're releasing ACE-Step-v1.5(2B), a fast, high-quality open-source music model.
— ACE Music (@acemusicAI) February 3, 2026
It runs locally on a consumer-grade GPU, generates a full song in under 2 seconds(on an A100), supports LoRA fine-tuning, and beats SUNO on common eval metrics.
GitHub: https://t.co/Y2CQETtltB
Key… pic.twitter.com/68OA1QQrrD
3月25日 Lyria 3 Pro ・ Lyria 3 Clip
3月25日 Suno v5.5
Meet Suno v5.5: More expressive, more you.
— Suno (@suno) March 26, 2026
Use your voice, your sound, and your taste to make music that's unmistakably yours, in the best and most personal Suno experience yet. pic.twitter.com/fKC7VAFLok
4月29日 Eleven Music
Today we are launching ElevenMusic, a new platform to discover, remix, create, and earn from music, built on the ElevenLabs music model. pic.twitter.com/wu7sdfiUCk
— ElevenLabs (@ElevenLabs) April 29, 2026
5月21日 Stable Audio 3.0
Meet Stable Audio 3.0, the open-weight model family built for artistic experimentation.
— Stability AI (@StabilityAI) May 20, 2026
This is our open invitation to experiment with generative audio. We believe the best innovations are still waiting to be built.
The 4-1-1 on 3.0:
📣 You own your outputs, and can distribute… pic.twitter.com/I6XE1949iB
8月13日 MiniMax-Music3
8月27日 Instrument X
9月9日 suno v6
9月10日 YuE2
10月30日 NemotronLabs RE-USE
Sound on 🔊 Listen to the difference.
— NVIDIA AI (@NVIDIAAI) October 30, 2026
Our new open multilingual NemotronLabs RE-USE model from NVIDIA researchers cleans up background noise, echo and other audio distortions to make speech clearer. All with just 9.6M parameters.
Try the demo and download the model on… pic.twitter.com/6WI8oj7u7t