Suno launches Speech (beta): AI voice plus music from text

Suno, the AI music platform, introduced a new feature called Speech in beta on October 1, 2026, letting users type an idea, poem, or piece of writing and generate a single track combining spoken voice and background music, available on both web and mobile.

Image: Suno · Source: suno.com

How Speech works

According to Suno's own announcement, Speech is built directly into the Suno creation flow: users type an idea, a poem, or something they've written, then describe the voice and musical style they want. Suno then produces one track that blends narration with original background music, rather than acting as a plain text-to-speech tool. The company's examples include bedtime stories set over soft piano, hype speeches over stadium drums, and ASMR-style grocery lists.

Platform availability

Suno's release notes list Speech as available on Android, iOS, web, and the Create screen inside the app. Before the wider rollout, Suno tested the feature internally with a small group of users for a month before opening the beta to everyone.

Beta limitations to know

Suno is upfront that this is still a beta: the company notes that British accents can occasionally drift into an Australian-sounding tone, and dramatic pauses can end up more dramatic than intended. Suno says it will keep refining Speech based on user feedback going forward.

The official announcement does not specify whether Speech is limited to certain subscription tiers (Free, Pro, Premier) or which languages beyond English are supported, so users wanting those details should check directly inside the app or on Suno's pricing page.