Suno, an AI music generator, has launched a new feature called "Speech" that combines spoken audio with synchronized background music in a single track. The feature generates text-to-speech content paired with original musical accompaniment, designed for applications like poems, meditations, and bedtime stories.
The Speech feature integrates Suno's existing music generation capabilities with voice synthesis. Users can input text, and the system produces both narration and complementary instrumental or musical backgrounds in one audio file. This differs from traditional workflows where users record speech separately and then add music in post-production.
Suno describes the feature as tailored for creators working with spoken-word content that benefits from musical accompaniment. The meditative and storytelling use cases suggest the company is positioning this tool for wellness applications, children's content, and creative projects requiring synchronized audio elements.
The company has not disclosed technical details about how the Speech model was trained. Specifics regarding training data sources, methodology, or whether the voice synthesis component uses existing third-party technology remain undisclosed.
Suno operates in a competitive AI music generation space alongside other tools like Udio and OpenAI's Jukebox. The addition of speech generation represents an expansion of the platform's capabilities beyond music-only generation. This move positions Suno as a more comprehensive audio creation tool rather than a single-purpose music generator.
The feature's release comes as AI audio tools continue expanding their feature sets. Suno's previous capabilities focused on music composition and generation across multiple genres. The Speech addition enables one-step creation of multimedia audio content, potentially reducing the complexity of producing podcast intros, guided meditations, audiobook narration, or similar content that requires both speech and music.
Users can now create complete audio projects within the Suno platform rather than relying on separate tools for voice and music production. The timing and specific availability of the Speech