Suno AI music platform launches speech generation feature
Suno introduces its new Speech feature in public beta, allowing users to generate synthetic voiceovers paired with AI background music up to eight minutes long.
Stock photo for illustration only, not from the actual event
- Suno launches Speech feature for AI-generated voiceovers
- Supports Simple and Advanced modes with voice customization
- Maximum duration reaches up to eight minutes in public beta
Suno, the popular AI music generation platform, is expanding beyond musical compositions by introducing a new feature called Speech. This tool is designed to generate synthetic spoken voices based on custom scripts or prompted descriptions, while simultaneously producing matching background music as a single cohesive audio track.
According to Jack Brody, Suno chief product officer, music remains at the core of the company, but their vision has always encompassed broader forms of human expression. The introduction of Speech marks the debut of an audio model that combines spoken words and background music together seamlessly.
Stock photo for illustration only, not from the actual event
While text-to-speech technology is far from groundbreaking—with industry players like Adobe and ElevenLabs, alongside DeepMind's decade-long research—Suno's entry into the space serves as a strategic move to diversify its platform, especially following numerous copyright lawsuits tied to its music generator.
Users can access the Speech feature across Suno's web and mobile platforms in public beta. The system offers multiple options and settings:
- Access via the Create tab by navigating to the Speech option
- Simple mode for descriptive prompts like a pirate captain rallying a crew
- Advanced mode for inputting exact custom scripts
- Customizable options for AI voice gender, speech style, and a maximum duration of around eight minutes
Suno's expansion into speech generation highlights a broader trend among generative audio developers to target practical content creation workflows, such as podcasts, audiobooks, and video voiceovers. By bundling background music directly with voice generation, the platform aims to streamline audio production. However, it also raises ongoing questions about how AI-generated speech tools will navigate content moderation and copyright frameworks moving forward.
The feature includes a toggle to easily disable the background music if clean spoken word is preferred, while various modes cater to different creative tones from calm poetry soundtracks to energetic dramatic speeches. Suno acknowledges that the beta software is not yet flawless; Brody noted with humor that British accents can occasionally drift to Australia and dramatic pauses might feel overly theatrical, while anticipating unique use cases discovered by early adopters.
Source: The Verge
Found something wrong in this article? Report an issue with this article
Comments
Leave a Comment