Design a voice by describing it: Gemini Flash TTS nails accents, laughs and filler words
jocarrasqueira · x · 2026-10-06
A demo of Gemini Flash TTS shows you can create a voice just by describing it — e.g. "warm, slightly raspy, Lisbon accent, speaks like she's telling you a secret." The output can naturally laugh and say filler words like "mhhm", making it appealing for podcasters and creators.
More from Multimodal
- OmniChar Adds Consistent Voice: 10-30s Sample Clones Speech Across AI Videos — ashishsanu · 2026-10-06
- Gothic vampire short film made with Seedance 2.5 on Runwayml — azed_ai · 2026-10-06
- AI-generated superheroes just want chai and biscuits, not saving the world — umesh_ai · 2026-10-06
- YarnGPT quietly ships Pidgin voice translation, more languages coming — saheedniyi_02 · 2026-10-06
- Doubao and Qwen voice models clone timbre from ~10s of audio, cheap enough for agents — AlchainHust · 2026-10-06
- Kling 4.0 Flash dialogue quality impresses: characters now act with pauses and eye contact — LudovicCreator · 2026-10-06