ModelsModels

Models#

The platform's speech engines. The registry is empirical: usableNow reflects real API probes, not marketing claims.

GET/v2/meta/engines

Engine registry#

EnginePipelineGermanUsable todayCost/minute
cartesiaCascade STT-LLM-TTSyesyes~0.02-0.05 EUR
cascade-togetherCascade STT-LLM-TTSyesyes~0.03-0.05 EUR
realtime-grokSpeech-to-speechyeskey-gated0.05 USD flat
realtime-openaiSpeech-to-speechyeskey-gated~0.06-0.11 EUR
agents-elevenlabsSpeech-to-speechyeskey-gated0.08 USD

Cartesia#

Cartesia is integrated as a first-class engine — with two operating modes behind one API:

ModeTTSSTTActivation
directSonic-3 via api.cartesia.ai (90 ms first byte)Inkconfigure CARTESIA_API_KEY
together-fallbackcartesia/sonic-2 via TogetherWhisper-large-v3 via Togetherautomatic without a key

Switching to the direct path requires no code change: once the key is present in the runtime environment, render and transcription switch over on their own. The active mode is always visible in /health (cartesia.mode) and in the X-Engine-Mode response header.

Direct path details: base https://api.cartesia.ai, auth Authorization: Bearer, mandatory Cartesia-Version header. Structured errors (error_code, request_id) are passed through.

Voice Library#

The platform ships a curated voice library (modeled after play.cartesia.ai/voices). Every entry is probed empirically against the live engine — nothing is listed that does not work.

GET/v2/audio/voices

Returns the merged library: engine base voices plus, once a CARTESIA_API_KEY is configured, the voices of your own Cartesia account (including playground favorites and clones). Favorites are tenant-scoped:

PUT/v2/audio/voices/{id}/favorite

Voices can be assigned per touchpoint script (voice_profile) and passed ad hoc to the render endpoint (voice). The console's WebWoW_Audio section provides preview, favorites, and assignment in one place.

Conversation LLM#

The conversational brain of the telephony is grok-4.20-0309-non-reasoning (~0.5 s response time, phone-grade) with grok-4.5 as fallback. Reasoning models are too slow on the phone.

Cartesia Line (assessment)#

Cartesia also offers "Line", a managed runtime for voice agents (deployment, turn-taking, call logs in Cartesia's cloud). CallFluence deliberately does not use Line: the platform architecture goes to the source (own ports, own edge) instead of into an orchestrator with lock-in. Cartesia's models (Sonic, Ink) are integrated through the platform's own engine layer — swappable like any other vendor.

CallFluence — voice AI platform. Last updated 2026-07-27.