Riverside Labs launches Tonality, a voice model that edits single words in existing recordings
aryanXmahajan · x · 2026-11-13
Riverside Labs launched Tonality, billed as the first voice model that can edit any single word in an existing recording while preserving the speaker's voice, pacing, accent and room acoustics. Unlike models that regenerate whole sentences, Tonality gives granular control over pitch, tone, duration, pauses, energy and pronunciation per word, supports in-line edits (change, insert, remove words), and works on both TTS and existing audio. API available; free playground with rate limits. The poster says a half-day re-recording session is now a straight edit.
More from Multimodal
- ACE teases new open-source music model claimed faster than Yue2 and ACE-Step 1.5 XL — bdsqlsz · 2026-11-13
- Gemini 4 Hydrogen passes the pelican-on-a-bicycle test in leaked render — Main_Exchange3944 · 2026-11-13
- MiniMax H3 Image lands in HyperFrames Studio: 16MP images in under 10 seconds — MiniMax_AI · 2026-11-13
- Same AI character, three models: hands-on with Seedream 5.5, MiniMax H3, GPT v2.6 — miilesus · 2026-11-13
- Seedance 2.5 suspense short: 'Then who made the coffee this morning?' — LudovicCreator · 2026-11-13
- Seedream 5.5 drops: 100+ edits on the same image with far less drift — minchoi · 2026-11-13