Suno has introduced a speech generation feature in public beta, allowing users to create voiceovers with optional background music.
Key facts
- •Suno's new speech feature is currently available in public beta on web and mobile.
- •The tool allows users to generate voiceovers with or without background music.
- •Users can choose between a prompt-based 'Simple' mode and a script-based 'Advanced' mode.
- •Advanced settings include options for voice gender, speech style, and generation variety.
- •The maximum duration for a generated speech track is approximately eight minutes.
The AI music platform Suno has expanded its capabilities by launching a new speech generation feature. Available in public beta on the company's web and mobile platforms, the tool allows users to generate spoken voiceovers based on scripts or descriptive prompts, with the option to include synchronized background music.
How the Speech Feature Works
Users can access the feature through the 'Create' tab by selecting the Speech option. The tool offers two modes: a 'Simple' mode that generates audio based on a descriptive prompt, and an 'Advanced' mode that allows for custom scripts. In the Advanced mode, users can adjust settings such as voice gender, speech style, and variety. The generated audio has a maximum duration of approximately eight minutes.
Development and Limitations
Suno Chief Product Officer Jack Brody described the tool as the first audio model capable of generating voice and music as a single cohesive track. The company acknowledged that the feature is in a beta phase and may experience inconsistencies, such as fluctuating accents or unpredictable dramatic pauses. Suno intends to refine the model based on user feedback.
Advertisement
This article was independently rewritten by ManyPress editorial AI from reporting originally published by The Verge AI.
