docs: add Inworld and MiniMax TTS engines#411
Merged
Conversation
- Add provider pages for Inworld and MiniMax under platform voice/TTS, each with models, full voice catalogs, languages, usage, voice parameters, and a build walkthrough (modeled on the Rime page). - Register both engines in the TTS index and the SWML languages voice engine list. - Document engine-specific params verified against the mod_openai C source: Inworld speakingRate/temperature; MiniMax speed/vol/pitch/ emotion plus emotion:auto. Added to ai_languages.tsp and the SWML languages reference. - Fix the TTS index table: add the missing azure. prefix to the Azure sample voice string and drop the redundant Engine code column.
Contributor
Change the sidebar/page title from 'The X TTS engine' to just the engine name for Inworld, MiniMax, and Rime, matching the convention used by ElevenLabs, Cartesia, Deepgram, Azure, and the other TTS provider pages. Drop the now-redundant 'Text-to-speech' subtitle.
- Replace the full voice catalog with a link-out section (TTS Playground + Inworld docs), matching the Rime/other-provider pattern. - Make the model cards non-link (both previously linked to the same page). - Frame the models table as 'SignalWire supports two Inworld models' and link to Inworld's model docs for detail.
- Replace the 332-row voice catalog with a link-out section pointing to MiniMax's System Voice ID List and TTS docs. - Add a warning that only MiniMax system voices work; cloned and AI-generated voices are not supported.
Remove the on-page 'Voice parameters' tables from the Inworld and MiniMax pages. Engine-specific params (speakingRate/temperature, speed/vol/pitch/emotion) are documented in the SWML ai.languages reference, matching how ElevenLabs and Cartesia params are handled.
The model table, cards, and intro all repeated mini/max. Consolidate to the cards (each now showing its model ID) plus the defaults note.
Manny-r31
approved these changes
Jun 15, 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
2 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 new TTS engines — Inworld (#194) and MiniMax (#195)
Changes
New provider pages (
fern/products/platform/pages/calling/voice/TTS/)inworld.mdxminimax.mdxTTS index (
index.mdx)azure.prefix.SWML spec + reference (
ai_languages.tsp,languages/index.mdx)inworldandminimaxto the selectable voice engines.languages[].params: InworldspeakingRate/temperature; MiniMaxspeed/vol/pitch/emotion.emotion: autofield to cover MiniMax (was Cartesia-only).yarn fern-md-checkpasses (all MDX valid); TypeSpec compiles.