Riverside launches Tonality, first voice model that edits single words in existing recordings
nikola_mr64990 · x · 2026-11-13
Riverside Labs introduced Tonality, billed as the first voice model that edits any word in an existing recording with full control over how it's said. Other voice models regenerate the whole sentence when one word changes, losing the original voice identity, delivery, and room acoustics. Tonality makes precise edits with control over pitch, tone, duration, pauses, energy, and pronunciation while everything else stays exactly as recorded. It's available via API with a free trial. Podcast editors note you can fix a mumbled word without asking the guest to re-record.
Related event: Riverside Launches Tonality, a Speech Model for Word-Level Audio Editing(2 posts)→
More from Multimodal
- From moodboard to 20-second teaser: a full coffee brand built in Adobe Firefly Boards and video editor — azed_ai · 2026-11-13
- Sgraffito Luminous Paradox: a reusable image-gen prompt template with striking results — LudovicCreator · 2026-11-13
- Dev builds vocal synth modeling vocal tract as branching acoustic tubes, not phoneme stitching — TinfoilTricorn · 2026-11-13
- AI-generated short 'Bubblegum Adventures': jobless Earthling begs for change — Zard-Oz · 2026-11-13
- AI-generated 'Stranger Beans (1975)' clip passes as a vintage B-movie — Mother-Pear-2392 · 2026-11-13
- AI reimagines Zelda: Breath of the Wild as a 1970s retro cartoon — techhalla · 2026-11-13