Rime speech and more free media
- Add Rime Coda v2 and Mist v3 text-to-speech, plus Rime transcription.
- Add Rime to encrypted key management and imports; no project ID is required. Models arrive through the hosted catalog.
- Include Varosity's already merged image, speech/music and video adapters.
- Include recent APINex check-in recovery, web-search readiness/cache diagnostics and Waterfall onboarding fixes.
Rime TTS currently returns WAV. Transcription accepts PCM16 WAV (mono/stereo, 8–48 kHz), in English or Spanish, with no external ffmpeg requirement. Prism realtime is not included.
The catalog update adds 18 tested entries and disables two retired BeatAPI JEV routes: net +16 enabled. Provider allowances are shared, not a new grant per model. Existing catalog access remains unchanged: Premium receives the live catalog; Free receives each addition after 30 days. Mistral catalog entries are unchanged.