Suno launches Speech Beta, combining voice and music in one model – Unite.AI

Suno announced Speech (beta) on October 1, 2026, releasing a spoken audio model that the company describes as the first to generate speech and music together as a single cohesive track. The beta opened to all users on mobile and web after a month of testing with a small group.

The announcement came in a company blog post written by Chief Product Officer Jack Brody. Speech creates spoken audio paired with original background music and is integrated directly into Suno: Users type an idea, poem, or something they’ve written, then describe the voice and musical style they have in mind.

A release note dated October 1, 2026 describes Speech as the first template to create a speech and its soundtrack together in a single take, and tags the voice for Android, iOS, Web, and Create. Its examples of what users might do include piano bedtime stories, stadium drum commercial speeches, and ASMR shopping lists, and says Speech is available on mobile devices and the web.

Suno frames the launch around what it calls creative entertainment, a category the company says will define the next wave of consumer technology. Music remains at the heart of what Suno builds, Brody wrote, as the company’s vision extends to other forms of human expression. The post describes Speech as another canvas for the personal creations its community already makes, pointing to songs users produce for birthdays, weddings, inside jokes, faith and worship, their children and their friends.

First uses and declared limitations of the beta

According to the post, the Suno team experimented with the model informally during development, turning friends’ text messages into dramatic readings, giving epic scores to ordinary voice notes, and creating meditations, poems, pep talks, and bedtime stories for their children.

Suno warned that the beta behaves like one in practice. A British accent can occasionally morph into an Australian one and vice versa, the company wrote, and “dramatic pauses can be very dramatic.” Suno said that users will almost certainly discover uses that had never occurred to the team, adding that this type of discovery is the purpose of opening the beta.

V6 and earlier versions from 2026

Speech follows a series of Suno releases documented in 2026. On September 9, 2026, the company introduced v6, a new generation of music models developed with industry partners Warner Music Group, BMG and Believe. Suno called the v6 models the best yet, describing them as faster, more expressive and of higher quality. The v6 family consists of three models: the flagship v6 and the exploration-oriented v6-wild, both available to Pro and Premier subscribers, and the v6-mini, a faster, more efficient version available to everyone.

Suno said v6 allows creators to edit part of an existing song using plain language, create a mashup from multiple sources in a single request, sample and isolate audio to create a new beat in a single workflow, create music from lyrics, audio, images and video, and update a single lyric without rebuilding the entire song. An example given by the company: changing a choir so that it is sung by a gospel choir.

Suno said its team hosts weekly writing camps with artists, producers, songwriters and musicians to learn how they use Suno in their creative workflows, and that it has introduced security measures to filter audio files and uploaded lyrics for unauthorized use. With the launch of the v6 version, the company said it plans to retire its previous models and move the platform entirely to the v6 generation. In the same announcement, Suno said it is developing participation experiences built around individual artists, where artists can choose to participate and get paid when they do so.

Previous entries in Suno’s release notes document the rest of the company’s 2026 product line. Suno launched version 5.5 on March 26, 2026, enhancing three features: Voices, which allows users to record or upload their own audio and sing over their creations; Custom Models, which train a custom version of v5.5 on at least six tracks from a user’s catalog; and My Taste, which learns the user’s favorite genres, moods and references over time. Vocals hit iOS and Android on August 7, 2026, allowing users to record a vocal once and use it on any song.

Suno released Studio 2.0, an overhaul of its browser-based generative audio workstation with MIDI editing, audio effects, built-in synthesizers, and a chat bar, to Premier subscribers on August 13, 2026. Further Studio updates on September 17, 2026, made transcription from MIDI to audio faster and more accurate than the source material.

Suno said he will continue to improve Speech as he learns what people like, what isn’t working yet, and what the community wants to do next. The release note asks users for feedback as the feature improves over time.