Suno launches Speech public beta: AI voiceovers with background music, up to about eight minutes
Suno has launched Speech in public beta on web and mobile. It generates spoken voice from a script or text prompt, with optional AI-generated background music, for clips up to roughly eight minutes. Suno claims it is the first audio model to generate voice and music together as one track.
Suno has launched Speech, a feature that generates spoken-word audio from a script or a descriptive prompt, in public beta on its web and mobile platforms. Users can generate a voiceover and matching AI background music in a single pass. Maximum output length is around eight minutes.
What Speech does
Speech sits in Suno's "Create" tab and has two modes:
- Simple: The user describes the desired output in a prompt box, for example "a pirate captain rallying his crew."
- Advanced: The user supplies a custom script for the voice to read verbatim.
Advanced settings let users adjust the voice's gender, speech style, and how much variety each generation has. The background music is optional and can be switched off with a toggle for clean speech. Suno positions the pairing for uses such as calm soundtracks under poetry, or more energetic music for dramatic voiceovers and motivational speeches.
Suno's claims
Suno chief product officer Jack Brody called Speech "the first audio model that generates voice and music together as one cohesive track." That is a company claim, and Suno has not published benchmarks or technical documentation to support it. Competing text-to-speech products from ElevenLabs, Adobe and others already exist, though the source does not indicate whether any of them combine voice and generated music in one output.
Brody was candid about the beta's limits: "Beta really does mean beta. Occasionally, British accents can wander off to Australia and back. Dramatic pauses may be very dramatic." Suno says it will refine the feature based on user feedback.
What has not been disclosed
- Model name and version: Suno has not given a version identifier for the Speech model.
- Pricing: Pricing and plan availability not yet disclosed.
- API access: Not mentioned in the announcement coverage.
- Parameter count, training data and benchmark scores: Not disclosed.
- Supported languages and accents: Not specified beyond Brody's reference to British accents.
What this means
Speech moves Suno from a single-purpose music generator into adjacent audio territory, where ElevenLabs is the best-known specialist. The differentiator Suno is betting on is integration: one generation yields voice and score together, which removes the manual mixing step creators now do after generating speech and music separately. Whether the quality holds up is untested, since no independent evaluations exist and Suno itself says the beta has rough edges such as accent drift.
The move also has a business angle. The Verge suggests Suno may be diversifying because its music generator has drawn numerous lawsuits. That is the outlet's interpretation, not a Suno statement. Speech output is not music, though the feature still generates background music, so it does not fully remove Suno from that exposure.
The eight-minute cap makes Speech suited to short-form content such as narration, ads and social clips, not long-form audiobooks. Watch for API availability, pricing, and independent voice-quality comparisons against dedicated text-to-speech providers.
Related Articles
Databricks opens Genie ZeroOps public beta after agent observed 80,000+ customer issues in private preview
Databricks opened Genie ZeroOps to public beta on November 19, 2026, after private-preview testing. The company says the autonomous data-pipeline agent observed more than 80,000 real customer issues during that limited preview.
Amazon Polly voice cloning is generally available as a gated release in seven languages
Amazon Polly voice cloning is now generally available as a gated release. It builds a custom voice on the Polly generative engine from a few minutes of one consenting speaker's audio, in seven languages. Building a voice is free, and usage is billed pay-as-you-go.
Nous Research brings open-source Hermes Agent to Microsoft Teams, adds Collective Wisdom skill sharing
Nous Research says companies will soon be able to run its open-source Hermes Agent directly in Microsoft Teams, with agents sandboxed in Azure Container Apps. A new feature, Collective Wisdom, lets employees share reviewed skills with colleagues, and the shared knowledge stays inside the company.
BioMap launches AI drug safety system with xTrimoTox, reports 0.9637 AUROC on liver injury
BioMap launched an AI-assisted nonclinical drug safety assessment system on November 19. It combines virtual-cell models, toxicity prediction and evaluation services, and the company reports AUROC of 0.9637 for drug-induced liver injury on a selected benchmark task.
Comments
Loading...