ElevenLabs Multilingual v2 is the higher-quality text-to-speech model across 32 languages, trading ~250-300ms of latency for better voice quality. Call POST /v1/audio/speech; `voice` takes an ElevenLabs voice_id.
curl https://conduit-api.bifrostapi.net/v1/audio/speech \
-H "Authorization: Bearer ck-YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"eleven-multilingual","input":"你好,世界"}' \
--output out.mp3→ Returns binary audio (audio/mpeg). Runs on the default voice; add "voice" with an ElevenLabs voice_id to choose another.
Auth, billing & streaming → Quickstart