★ 第 23 单元

Voice, AI devices and robots

Design for the ear, the hands and the room. Learn voice UI and conversation design, build voices and voice agents with ElevenLabs, design for people who dictate everything with tools like Wispr Flow, make a sonic brand with AI music tools like Suno, and design honest screenless devices and robots. You'll prototype with real speech in the browser and test prompts on a real model as you go.

🔒 第 23 单元仅限会员

第 7 至 25 单元仅向训练营会员开放。如果你是学员请登录，或申请加入。

登录返回免费课程

1Designing for voiceKnow when voice is the right interface, and design turns, confirmations and errors the way good conversations work.
2Conversation designWrite sample dialogues, plan happy and unhappy paths, give your agent a persona, and write a system prompt for a voice agent.
3Building with ElevenLabsChoose and tune a voice, call a text-to-speech API, plan for latency and interruptions, and use voice cloning responsibly.
4How voice agents workUnderstand the speech-to-text, language model and text-to-speech pipeline, design for its latency, and let the agent take real actions with tool calls.
5Dictation-first designDesign text fields, commands and editing flows that work for people who type with their voice, using tools like Wispr Flow.
6AI music and sound with SunoPlan a sonic brand, prompt an AI music tool for a jingle with well-structured lyrics, and handle rights, licensing and sound-alike risks.
7AI devices and robotsDesign for screenless and ambient devices and for robots, matching what they seem to be with what they can really do, and keeping people safe.
8Testing voice experiencesTest voice designs before they're built, review transcripts, measure task success and recognition, include diverse voices, and evaluate AI voice agents.
★A voice experience for Crumb Club项目