docs: add Cartesia support to pronunciation dictionaries#1041
Open
dhruva-reddy wants to merge 1 commit intomainfrom
Open
docs: add Cartesia support to pronunciation dictionaries#1041dhruva-reddy wants to merge 1 commit intomainfrom
dhruva-reddy wants to merge 1 commit intomainfrom
Conversation
PR #11683 (Cartesia sonic-3 validation gate) merged, so customers can now attach pronunciation dictionaries to Cartesia voices via voice.pronunciationDictId. This page previously claimed pronunciation dictionaries were "exclusive to ElevenLabs" — update to cover both providers with parallel implementation examples, BYOK behavior, and the upstream-resourceId vs Vapi-UUID gotcha.
Contributor
|
🌿 Preview your docs: https://vapi-preview-55705b26-f2dd-49d5-8c42-cb10fffe7f34.docs.buildwithfern.com |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
fern/assistants/pronunciation-dictionaries.mdxto cover Cartesia in addition to ElevenLabs<Tabs>with parallel Cartesia / ElevenLabs flowsFound credentials for {provider}. Use {provider}'s API with your own credentials...rejection that fires for both Cartesia and ElevenLabs BYOK orgsresourceIdvs Vapi UUID footgun — the most common customer mistake when wiring a newly-created dictionary onto a voice{provider}placeholder for List / Update / Delete endpointsResolves PRISM-474 deliverable #5.
This PR is unblocked now that PR #11683 (VapiAI/vapi: feat(voice): require sonic-3 model when Cartesia pronunciationDictId is set) has merged. The previous version of this page claimed pronunciation dictionaries were "exclusive to ElevenLabs" — that's no longer accurate.
Related Vapi PRs (for context)
sonic-3for CartesiapronunciationDictId(MERGED)voiceWarningsfield on assistantfindOne) (OPEN)<PronunciationDictionarySelect>picker UI for both providers (OPEN)When PRs #11691 / #11698 / #11715 land, a follow-up docs PR can add: stale-ref detection /
voiceWarnings, dashboard UI screenshots, and the dashboard-driven flow.Testing Steps
fern check— passes with 0 errors (5 pre-existing warnings)<Tabs>for Cartesia/ElevenLabs split and the<Warning>callouts)assistants/pronunciation-dictionariesis unchanged (nodocs.ymlupdate needed)YOUR_API_KEYplaceholder, no real keys committedProcess notes
This PR skips the test-writer / code-reviewer phases per the project rule for docs-only PRs.