Model Catalog
Model catalog
Every voice model, priced and mapped by region
Compare speech-to-text and text-to-speech models from leading providers. Filter by the regions and languages you need, then call any of them through one API.
API price
Per model/min
Call any model directly through one API. You pay that model's rate per minute, shown on each card below.
Agent bundle price
$0.003/agent-min
Run models inside your voice agent on the SLNG execution layer. One flat rate, whichever model you pick.
The catalog is temporarily unavailable. Browse every model in the docs catalog.
Does my voice AI data stay in-region?
Yes. Audio processed in a region stays in that region. Every call is logged with region, provider, model, and timestamp. You swap your base URL to the region of your choice.
Is SLNG compliant with GDPR?
GDPR compliant. ISO 27001 and SOC 2 Type II certified. HIPAA compliant. Details at trust.slng.ai.
What does "per agent minute" mean?
Agent minute is the length of the call, not the amount of audio processed. A 3-minute call is 3 agent minutes regardless of how much silence or overlap it contains.
How do I integrate SLNG with my voice AI stack?
Swap your STT, LLM, and TTS endpoints to SLNG. No changes to your orchestrator, your models, or your agent logic. Works with LiveKit, Pipecat, Cognigy, or any custom stack.
Which models are supported?
30+ models across STT, TTS, and LLM. Providers include Deepgram Nova 3, ElevenLabs, Cartesia Sonic, Soniox, Rime Arcana, Sarvam, and Whisper. Models are available as SLNG Hosted, SLNG Proxied, or BYOK. Full catalog at docs.slng.ai/models.
