AI music maker Suno now generates spoken words
Suno, an AI music generation platform, has launched a new Speech feature in public beta that generates spoken voices from scripts or descriptions. The innovation allows users to create voiceovers and background music simultaneously, with the music automatically complementing the generated speech. This expansion reflects Suno's broader vision beyond music creation, particularly significant given the company's music generator has attracted numerous lawsuits in recent months.
The Speech feature is available on Suno's web and mobile platforms and operates in two modes: Simple (using descriptive prompts like "a pirate captain rallying his crew") and Advanced (with custom scripts). Users can adjust the AI voice's gender, speech style and variation level, with a maximum duration of approximately eight minutes. The background music is optional and can be toggled off for clean speech alone. Whilst Suno acknowledges imperfections in the current beta, such as British accents occasionally shifting to Australian ones and overly dramatic pauses, the company says it will refine the feature based on user feedback. Other platforms offering AI-generated speech include DeepMind, Adobe and ElevenLabs, which launched in 2023.
- Music generator Suno now generates spoken voices with optional background music
- Feature available in public beta on web and mobile platforms
- Company acknowledges beta has imperfections but plans improvements
New here? Start with this
Suno is an artificial intelligence company whose platform generates music. Users can create original songs and instrumental tracks using AI without requiring musical training. The company has recently faced lawsuits from music publishers and artists who claim its system was trained on copyrighted material without permission.
The company has now launched a feature that generates spoken voices from text, expanding its capabilities beyond music creation. This new speech tool can create voiceovers that work alongside background music, marking Suno's entry into a broader audio creation space. The expansion reflects how AI audio platforms are diversifying their offerings.
Other companies also provide AI-generated speech tools, including Adobe, DeepMind and ElevenLabs. This reflects a growing commercial market for AI audio generation, with multiple platforms competing to offer different audio creation capabilities. The competitive landscape indicates how this technology is becoming increasingly established and accessible.