OpenAI shows how to shape GPT-Live-1 voices via prompts and new presets
pbbakkum · x · 2026-10-17
OpenAI's developer account details how to give apps built on GPT-Live-1 a fitting voice: shape it via a prompt or pick from newly added international preset voices. The playground and API are available for trying it out.
The rebroadcast promotes the entry point with a playful "every voice starts with a spell" framing.
More from Multimodal
- S4VY: Segment Anything in 4D, with consistent identity across space and time — realChrisChoy · 2026-10-17
- Creator builds "Claudia x Roadster" film with Claude, MCP, Midjourney and BytePlus — elonmusk · 2026-10-17
- Voyager launches AI harness for creative work with per-second GPU cloud Blender rendering — ravisparikh · 2026-10-17
- Fish Audio's Drama 3 directs AI voice emotion via natural language, open weights — Aiden_Tech_Ai · 2026-10-17
- Gemini 4 Argon costs 43¢ vs Opus 5.5's $2.43 on same build prompt — MattVidPro · 2026-10-17
- Multiverse Releases Comet 60B: Open Multimodal Model Built on Nemotron, Half the Params — NVIDIAAI · 2026-10-17