Suno Speech

AI music platform Suno launched a public beta for a new feature named Speech, according to an announcement by the company's chief product officer. The software generates spoken word narration combined directly with an original background music score in a single file. Users can type in written text, such as a script or poem, and specify both the vocal style and the musical genre they want accompanying it.

This update simplifies audio creation for everyday users and online creators. Instead of using separate tools to record a voiceover and compose a background track, people can generate customized audio using simple text prompts. The tool opens up practical and playful applications, such as turning standard text messages into dramatic readings, generating custom ambient audio, or producing personalized bedtime stories.

Because the feature is currently in beta, the audio output can be inconsistent. Suno noted that regional accents might shift unexpectedly during a track and pauses can sometimes sound overly dramatic. It remains unclear how well the software will handle longer scripts or precise timing adjustments needed for professional editing. As generative tools streamline voice and soundtrack creation, traditional royalty-free audio libraries may need to adapt to compete with on-demand synthetic production.