openai · OpenAI Platform Docs
Voice agents
Teaches how to architect and implement voice-based AI agents using either a direct speech-to-speech model via live audio sessions or a chained workflow involving speech-to-text, text reasoning, and text-to-speech.
Derived skill
Files assembled from official documentation
Viewing SKILL.md
Voice agents
Teaches how to architect and implement voice-based AI agents using either a direct speech-to-speech model via live audio sessions or a chained workflow involving speech-to-text, text reasoning, and text-to-speech.
When To Use
Use when deciding between a low-latency speech-to-speech architecture or a controlled chained voice pipeline and implementing the corresponding WebRTC or SDK-based workflows.
Reference Files
| File | Contains | Use For |
|---|---|---|
SKILL.md | Entry point: scope, routing table, and workflow. | Start here. |
docs/voice-agents-workflow-guide.md | A guide explaining architectural choices for building speech-to-speech voice agents and chained voice workflows. | Questions about a guide explaining architectural choices for building speech-to-speech voice agents and chained voice workflows. |
What This Skill Covers
- Voice agents turn the same agent concepts into spoken, low-latency interactions. The key design choice is deciding whether the model should work directly wit...
- Main sections:
Choose the right architecture,Recommended starting points,Build a speech-to-speech voice agent,Build a chained voice workflow,Voice agents still use the same core agent building blocks.
Workflow
- Open the most relevant file under
docs/for the exact documented workflow and wording. - Open
schemas/files for exact structured contracts. - Open
examples/files for concrete requests, commands, snippets, and manifests. - Do not add behavior or configuration that is not present in the attached source files.
Canonical source: https://developers.openai.com/api/docs/guides/voice-agents.md