[Agents] Add voice agents docs and update browser tools - #29834
Merged
Conversation
Add a new Voice agents API reference and a Build-a-voice-agent guide; introduce real-time voice agent docs (withVoice, withVoiceInput, client hooks, providers, Telephony, examples, and Durable Object config). Rewrite and expand the Browse the web doc into a browser tools reference (CDP-based browser_search/browser_execute tools, usage, examples, CDP helper API, security considerations, limitations, Puppeteer/Browserbase examples, and config). Also update agents index to reference browser tools and voice agents and make small example/content tweaks.
github-actions
Bot
added
product:agents
github-actions
Bot
assigned
elithrar,
irvinebroque,
rita3ko,
thomasgauvin and
whoiskatrin
threepointone
marked this pull request as ready for review
April 14, 2026 09:43
threepointone
requested review from
elithrar,
irvinebroque,
rita3ko,
thomasgauvin and
whoiskatrin
as code owners
April 14, 2026 09:43
Contributor
|
This pull request requires reviews from CODEOWNERS as it changes files that match the following patterns:
|
![devin-ai-integration[bot]](https://avatars.githubusercontent.com/in/811515?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
Fixes TOML scoping bug where compatibility_flags ended up inside worker_loaders table, and fixes MYBROWSER/BROWSER binding mismatch in Puppeteer section. Made-with: Cursor
Contributor
whoiskatrin
approved these changes
Apr 14, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
6 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds documentation for two recently shipped Agents SDK features: voice agents (
@cloudflare/voice) and browser tools (agents/browser).New pages:
api-reference/voice.mdx— Full reference forwithVoice,withVoiceInput, React hooks (useVoiceAgent,useVoiceInput),VoiceClient, Workers AI and third-party providers, telephony (Twilio), pipeline hooks, conversation persistence.guides/build-a-voice-agent.mdx— Step-by-step tutorial: scaffold a project, wire up STT + LLM + TTS, build a React client, add pipeline hooks and third-party providers.Updated pages:
api-reference/browse-the-web.mdx— Rewritten to lead with the new CDP-basedagents/browsertools (createBrowserToolsfor AI SDK and TanStack AI), CDP helper API reference, configuration, security model, and limitations. Puppeteer and Browserbase kept as alternatives below the fold.index.mdx— Updated "Browse the web" bullet and added "Talk to users" bullet for voice agents.Source content synced from the agents repo (
docs/browse-the-web.mdanddocs/voice.md).Documentation checklist
Made with Cursor