Suno releases Speech beta, generating narration and background music as one track
Suno released Speech (beta) on October 1, 2026. It generates voice narration and optional background music in one track, on all plans, with Simple and Advanced modes.
Suno releases Speech beta, generating narration and background music as one track
Suno released Speech (beta) on October 1, 2026, according to a Suno post on X as cited by AI Matters. The feature creates spoken audio from a user's idea or script, with or without background music. Suno's blog, as reported, calls it the first audio model that generates voice and music together as one consistent track. Suno tested it with a small group of users for one month before opening the beta. Suno's help center says it is available on all plans. Simple mode takes one prompt that describes the voice, mood and music. Advanced mode adds a Script field, a Tone field, vocal gender, a background music toggle and a Variety setting that controls style differences between generations.
The release moves Suno from songs into general spoken audio. It follows Suno Visuals, which turned tracks into video on November 17, and the v6 music model built on licensed Warner Music Group, BMG and Believe catalogs in September. Suno's blog lists meditation, poem, encouragement speech and bedtime story as test uses. Per the AI Market Watch index, Suno has $775M in total funding. That index tracks about 5,000 companies, so it is coverage, not a census. Suno reported beta issues: a British accent sometimes switched to Australian and back, and dramatic pauses sometimes ran too long.
For builders, narration and music no longer need two tools and a manual mix. A team producing podcast intros, guided audio or short announcements can test single-pass output on any Suno plan. Check accent consistency and pause timing before production use, because Suno itself describes those as beta problems.

