Episode Details

Anyone can make a voice say a sentence. Designing one you can listen to for hours is a different problem. This episode breaks down how modern text-to-speech voice design actually works: the two families of methods (describe-and-preview casting versus reference-audio speaker embeddings), what the ElevenLabs sliders really do, why identity and colour are separate signals, and what research on professional radio voices reveals about warmth, pitch depth, and staying pleasant across a long drive. Key sources: • ElevenLabs Voice Design quickstart — https://elevenlabs.io/docs/eleven-api/guides/how-to/voices/voice-design.mdx • ElevenLabs voice settings reference (stability, similarity_boost, style, speed, speaker boost) — https://github.com/elevenlabs/skills/blob/main/text-to-speech/references/voice-settings.md • ElevenLabs Voice Design product page — https://elevenlabs.io/voice-design Episode 6229 — myweirdprompts.com/n/6229 (permanent short link: myweirdprompts.com/482544)