AI music generator Suno can now create spoken audio with matching background music
Suno's Speech feature turns poems and meditations into audio with AI-matched background music in one track.
Why it matters
Suno expands its music-generation product into multimodal audio creation, but the company has disclosed nothing about model training or potential training-data sourcing—a gap that matters for practitioners evaluating content-generation tools.
The key facts
9 to knowFeature: Suno adds 'Speech' capability to create spoken text + background music in single track
Stated use cases: poems, meditations, bedtime stories
Model training method: undisclosed
Status: feature launch (no GA date or beta eligibility criteria stated)
Multimodal integration: text-to-speech + music generation in single model or pipeline not specified
Feature called 'Speech' combines spoken text with matching background music in single audio track
Use cases: poems, meditations, bedtime stories
Suno has not disclosed model training methodology
Status: appears to be a new product feature, not yet confirmed GA or beta timeline
The story so far
Earlier coverage of this storyline
- AI music maker Suno now generates spoken wordsThe Verge AI
- This story
Go to the source
The Decoderthe-decoder.com
Publisher excerpt: Suno is adding a feature called "Speech" to its AI music generator that creates spoken text with matching background music in a single audio track. The company says it's built for things like poems, meditations, and bedtime stories. Suno hasn't said how the model was trained.