Skip to content

docs: Soniox end-of-turn, OpenAI prompt caching, Twilio transport, video recording - #1445

Closed
dhruva-vapi wants to merge 1 commit into
mainfrom
devin/1795219830-docs-soniox-openai-twilio-video
Closed

dhruva-vapi wants to merge 1 commit into
mainfrom
devin/1795219830-docs-soniox-openai-twilio-video

Conversation

@dhruva-vapi

@dhruva-vapi dhruva-vapi commented Nov 21, 2026 •

Copy link
Copy Markdown
Contributor

Description

Documents four shipped settings that customers can configure but the docs did not cover:

  • Soniox (providers/transcriber/soniox.mdx): new "End-of-turn detection" section covering endpointSensitivity (default 0.3) and endpointLatencyAdjustmentLevel (default 2). Both apply to stt-rt-v5/v6 only, not v4. Adds tuning guidance.
  • OpenAI (providers/model/openai.mdx): new "Prompt caching" section explaining promptCacheKey and promptCacheRetention (in_memory / 24h) in plain terms. Both are unset by default. understanding-cost.mdx now links to it.
  • Twilio (phone-numbers/import-twilio.mdx): new "Outbound transport settings" section for transportConfigurations: ring timeout (default 60s), record (requires your own Twilio credentials) and recordingChannels (mono / dual). These are API-only and apply to outbound calls and warm-transfer legs. call-recording.mdx now cross-links to it.
  • Video recording (assistants/call-recording.mdx): new section covering where the URL lands (call.artifact.videoRecordingUrl), that recording works on Daily web calls only, that it is disabled for ZDR/PCI, and videoRecordingStartMode (client / server) on POST /call/web.

Every field name and default was checked against VapiAI/vapi source. Deliberately left out because they are still behind feature flags: Code tools, Deepgram Flux TTS and Microsoft (MAI) voices.

Testing Steps

  • npx --yes fern-api check: 0 errors (15 warnings, the same as on main)
  • Check the changed pages in the preview deployment
  • Confirm the OpenAIModel API-reference anchor link resolves

Technical Writer opened this PR for Dhruva
Implemented in session Update docs for recent product changes
Review with Devin · Open in Devin Desktop


Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
@devin-ai-integration

Copy link
Copy Markdown
Contributor

I'll fix CI failures and address comments from users with write access that start with 'Devin'.

  • Disable automatic comment, CI, and merge conflict monitoring

@devin-ai-integration devin-ai-integration Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

✅ Devin Review: No Issues Found

Devin Review analyzed this PR and found no bugs or issues to report.

Devin Review

@devin-ai-integration

Copy link
Copy Markdown
Contributor

Devin Review

🟢 Devin Review found nothing to fix · View findings

@github-actions

Copy link
Copy Markdown
Contributor

@devin-ai-integration

Copy link
Copy Markdown
Contributor

Split into stacked PRs #1446 (Soniox), #1447 (OpenAI caching), #1448 (Twilio transport), #1449 (video recording).

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant