Saved toolsSubmit a tool
AI TOOL

Miya is a personal music AI agent that, through conversation, can describe experiences, lyrics, emotions, or preferred styles to explore songs, playlists, and remixes; it can also create music videos by combining photos. The public page provides input fields for text, photos, and audio, along with example use cases.

Claim toolCompare toolsReport a correction—
SHARE / FOXAI

Share tool · miya.fm

What is miya.fm?

Miya organizes song listening and creation through natural language dialogue. Users can describe a scene, mood, musical style, or favorite works to find corresponding playlists, or share their experiences or provide lyrics to further refine the song’s expression.

The official website showcases examples such as audio adaptations and photo‑music videos, and provides links to image and audio attachments. Conversations can be used to modify style, plot, and presentation; the specific durations and generation speeds shown in the examples do not represent fixed completion times for any given request.

The current site is labeled as beta; please confirm the actual tasks and account requirements before you begin. When adapting existing songs, photos, or audio, you must obtain the necessary permissions. A public demonstration does not imply that the platform holds any commercial license for the works presented, nor does it guarantee that the results will be an exact word-for-word, note-for-note match with the original piece.

Key features

  • Conversational Songwriting

  • Mood and Style Playlist

  • Audio adaptation for reference

  • Photo combined with music video

  • Multiple rounds of creative adjustments

Use cases and audience

Music enthusiasts and personal music video creators

  • Personal and commemorative songs
  • Scene Playlist Exploration
  • Style adaptation of licensed audio
Input

Experiences, lyrics, style descriptions, and licensable photos and audio

Output

Songs, playlists, remixes, and music videos

You may also like

View all

Suno is an AI music platform that creates songs from text descriptions, lyrics, and reference materials. Users can generate vocal tracks or instrumental music, then use features like editing, remixing, and audio track separation to further produce and share their creations.

Free entry availableView details

IBM Text to Speech is an API service that converts text into natural-sounding speech. It supports multilingual neural voices in applications or Watsonx Assistant, allows you to adjust pronunciation and speech rate via SSML, and offers branded voices and various deployment options for specific use cases.

View details