AI music maker Suno now generates spoken words
Original reporting by The Verge
Suno's new Speech feature refers to the company's expansion into AI-generated spoken voices, allowing users to create voiceovers based on scripts or prompted descriptions, often accompanied by background music. Traditionally known for its AI music generation, Suno is now offering Speech in public beta across its platforms, enabling the simultaneous creation of voice and music within a single cohesive track. This move positions Suno alongside established players like ElevenLabs and Adobe in the text-to-speech domain.
A unique approach
What differentiates Suno's offering is its integrated approach: users can opt to pair generated speech with AI music, tailoring the soundtrack to the spoken word's purpose, such as calming music for poetry or energetic tones for speeches. While the background music is optional, this combination aims to enhance specific use cases for generative audio. Users can access Simple mode for descriptive prompts or Advanced mode for custom scripts, with options to adjust voice gender, style, and variety. Suno acknowledges the beta status, anticipating further refinements based on user feedback.
Suno’s expansion into AI speech generation, particularly its unique offering of voice and music within a single cohesive track, represents a strategic pivot designed to diversify its platform and appeal to a broader user base. While the text-to-speech market is already robust with established players, Suno’s integrated approach provides a distinct value proposition for creators seeking comprehensive audio solutions, whether for podcasts, educational content, or narrative experiences. This move, still in public beta, acknowledges the nascent stage of the technology, promising further refinements based on user feedback.
The Shifting Landscape
Beyond Suno's immediate offering, this development underscores a significant trend in the evolving AI audio landscape. The integration of high-quality speech and music generation into a single platform signals a future where content creation tools are increasingly multimodal and sophisticated. For content creators, educators, and even advertisers, such integrated suites could drastically reduce production overheads, democratize access to professional-grade audio, and unleash new forms of creative expression. However, it also amplifies existing concerns regarding authenticity, the potential for misuse in generating synthetic voices, and the ethical implications for the human voice industry. As AI models continue to advance in realism and emotional nuance, the boundaries between human and machine-generated audio will increasingly blur, urging stakeholders to consider responsible deployment and clear disclosure as these powerful tools become more prevalent. Suno’s venture is not just about a new feature; it’s a glimpse into the integrated, AI-powered audio future.
Frequently asked questions
- What new AI audio feature did Suno launch, and how does it stand out?
- Suno has introduced "Speech," a new feature that generates spoken voices from scripts or prompted descriptions. Its unique differentiator is the ability to simultaneously generate voiceovers and complementary background music as a single, cohesive audio track. While other platforms offer AI speech synthesis, Suno's integration of music with generated voices provides a distinct creative tool for various expressive use cases.
- How do users generate AI voices and music using Suno's new Speech feature?
- To use Suno's Speech feature, users access the "Create" tab and select the "Speech" option. They can choose "Simple" mode to describe their desired output via a prompt, or "Advanced" mode to input a custom script. Advanced settings also allow adjustments to the AI voice's gender, speech style, and generation variety. The generated audio can include both speech and background music, or speech alone if preferred, with a maximum duration of approximately eight minutes.
- Is Suno's new AI speech and music generation feature fully developed?
- Suno's new Speech feature is currently available in public beta. While functional, the company acknowledges it is still undergoing improvements based on user feedback. Users might encounter occasional quirks, such as accent variations or overly dramatic pauses. Suno intends to refine the model continuously, recognizing that beta testing will uncover diverse and unexpected applications for the integrated voice and music generation capabilities.