A beta model that turns a prompt, a poem, or your own writing into AI narration with an original score generated together — Suno's first product beyond song generation.
2026-10-02 · by Moe Ameen
Suno released Speech, a beta spoken-word model, on October 1, 2026. The company describes it as the first audio model that generates voice and music together as one cohesive track. After about a month of testing with a small group, the beta opened to all users on mobile and web — iOS, Android, and the web app. It is Suno's first product that reaches beyond song generation.
The flow is simple: type an idea, a poem, or something you have written, then describe the voice and musical style you want. Suno generates the narration and its backing score in a single pass instead of making you record speech and stitch music under it by hand. Suno's own examples range from bedtime stories over soft piano to hype speeches over stadium drums to ASMR, and according to reporting at launch the background music is optional, with a toggle that switches it off for anyone who wants speech alone.
Suno is candid that this is a beta. The company notes that a British accent can occasionally drift into an Australian one and back, and that "dramatic pauses may be _very_ dramatic." Early coverage also notes the beta does not advertise controls for exact duration, word-level timing, or cloning a voice from a reference recording. Chief product officer Jack Brody framed the release as an expansion rather than a pivot, writing that "music will always be at the heart of Suno and what we build."
The launch lands as Suno — reportedly valued above $5 billion with more than two million subscribers — pushes past music into the broader spoken-audio space that dedicated voice tools like ElevenLabs occupy. It also arrives while the company is still fighting the RIAA's training-data lawsuit, so the same provenance questions that hang over its music apply to anyone using the spoken-word output commercially.
Here is the move the day Speech ships: a narration track is an audio file, and audio files do not trend — the spoken word has to become something watchable. Generate the voiceover in Suno Speech, then bring it into [Kompozy](/) as the audio bed. Because the track is speech, it caption-maps almost perfectly: Kompozy burns the narration in as word-synced on-screen text over a portrait video clip, so a bedtime story, a poem, or a hype monologue becomes a 9:16 short that reads with the sound off — the way most feeds autoplay. If the piece runs long, [Clipped Shorts](/glossary/clipped-short) cut it into several standalone moments instead of one.
From there, one narration becomes a week. Kompozy fans the same script into quote graphics pulled from the strongest lines, a brand-exact [Carousel](/glossary/hyperframes) that teases the audio, native text posts, a Blog Article, and an Email Newsletter — all held to one voice by your [Persona Brief](/glossary/persona-brief) — then schedules and publishes the set across eight social platforms plus blog and email with [Autopilot](/glossary/autopilot) and a per-post review step. One practical note given Suno's open copyright fight: Kompozy is source-agnostic, so if you would rather pair a monetized post with a voice or track you can stand behind, the pipeline does not change. Suno writes and performs the words; Kompozy turns them into a watched, published presence. See [content repurposing](/glossary/content-repurposing) for the fuller one-source-to-many-outputs workflow.
Speech is Suno's beta spoken-word model, launched October 1, 2026. You type an idea, a poem, or your own writing and describe the voice and musical style, and it generates the narration and an original backing score together in one track. It is Suno's first product beyond generating songs.
Suno released Speech in beta on October 1, 2026, opening it to all users on mobile and web (iOS, Android, and the web app) after about a month of private testing with a small group.
By default it generates voice and an original score together, but reporting at launch says background music is optional and a toggle turns it off for anyone who wants speech alone. Suno notes it is a beta — accents can drift and dramatic pauses can become exaggerated.
Suno makes the audio and stops there. Bring the narration into Kompozy as the audio bed, burn in word-synced captions over a portrait clip, clip a long piece into several shorts, then fan the script into a carousel, quote graphics, a blog, and a newsletter and publish across eight social platforms plus blog and email.