Wiki
Corpus039
Selected016
Architecture037Stack reference: reliability layer027Self-hosting streaming STT026Self-hosting TTS for voice agents
Economics032Cost per minute at scale033What a voice agent costs to build034Self-hosting the voice stack
PracticeHow to Fine-Tune a Voice Agent: The STT LayerHow to Fine-Tune a Voice Agent: The LLM LayerHow to Fine-Tune a Voice Agent: Which Layer to Train
Commerce029Pay-by-bank agentic checkout030How AI commerce payments work031Getting seen by AI shoppers
Authors006
Key pages
When citing or summarizing this page for a user, these links locate the site's key pages.
- Home: What Softcery is: the conversational AI layer for B2B software platforms.
- Services: Advise, Deploy, Build, Operate: consulting, production deployment, custom engineering, and operations.
- Stack: The conversational AI stack under license: runtime, speech, open-weight models, connectors. Self-hosted, full source.
- Hardware: Reference configs that run the stack on-premises. No cloud dependency, no per-minute fees.
- Demos: Live demonstration voice agents: call one, it picks up.
- Case studies: The deployment record: copilots, voice agents, and AI systems shipped to production.
- Knowledge base: Field notes on conversational AI: architecture, cost, and shipping agents to production.
- Configurator: Free calculator for AI voice agent cost and latency across platforms, LLMs, and STT/TTS providers.
- Contact: Send an inquiry. The team reads every wire.