# Suno adds spoken‑word generation to its AI music tool

> Suno’s voice feature enters public beta, letting users create up to eight‑minute tracks that combine AI‑generated speech and music.

Oossa · 2026-10-02 · https://oossa.com/en/suno-adds-spoken-word-generation-to-its-ai-music-tool

Suno has launched a public beta for a new Speech feature. The tool can turn a script or a short description into spoken words and add background music in the same file. It works on Suno’s website and mobile app. Users can switch the music on or off, and they can choose a simple prompt or write a full script. The longest clip the beta will produce is about eight minutes.

## How the feature works

In the Simple mode, you type a description like “a pirate captain rallying his crew” and the AI creates a voice and a matching soundtrack. In Advanced mode you paste a script, pick the voice gender, set a speech style, and control how much variation the AI adds. The beta is still experimental – Suno says British accents sometimes drift to Australian, and pauses can be overly dramatic.

## What’s new compared to other tools

Unlike most text‑to‑speech services, Suno’s model generates voice and music together as a single track. The music component can be muted if you only need clean speech. Suno hopes the combo will be useful for things like poetic readings with a calming backdrop or energetic voiceovers for presentations.

## The facts

- Suno opened the Speech feature to a public beta on Oct 2, 2026.
- The beta works on both Suno’s web platform and its mobile app.
- Speech can produce tracks up to roughly eight minutes long.
- Two creation modes are offered: Simple (prompt‑based) and Advanced (script‑based).
- Advanced settings let users adjust voice gender, speech style, and variation.

## Why it matters

For creators who already use Suno for music, the new voice option means they can add narration or dialogue without leaving the platform. It could simplify making short audio ads, podcasts, or classroom recordings, though the output still needs editing because the beta sometimes mispronounces words or adds odd pauses.

## Sources & references

1. [AI music maker Suno now generates spoken words](https://www.theverge.com/ai-artificial-intelligence/1003925/suno-speech-ai-voice-feature-beta-availability) – The Verge, 2026-10-02
2. [AI music generator Suno can now create spoken audio with matching background music](https://the-decoder.com/ai-music-generator-suno-can-now-create-spoken-audio-with-matching-background-music/) – The Decoder, 2026-10-02

Last updated: 2026-10-02