VaxVoIP Agent AI SDK

VoiceBun is an open source, no-code voice-agent builder that lets you create, configure, and deploy AI-powered conversational assistants entirely via natural-language prompts. It combines speech-to-text, large-language models, and text-to-speech into a unified platform where you define your agent’s goals, initial greeting, tool integrations and data sources; VoiceBun automatically generates the underlying conversational logic, state management and API connectors needed to handle inbound and outbound calls for support, scheduling, lead qualification and more. The web-based interface gives you mobile-friendly access and isolated deployments through user-specific subdomains, while built-in analytics surface call transcripts, usage metrics, success rates, and sentiment trends. Integration includes options for telephony, webhook actions for external workflows, and role-based access controls with encrypted credentials for enterprise security.

Grok Voice Agent Builder is xAI’s no-code platform for configuring production voice agents on Grok Voice in under two minutes. It is built for operators and developers who want high-volume voice agents without building the surrounding stack from scratch, bringing telephony, knowledge retrieval, tools, guardrails, MCPs, and observability into one place. Instead of stitching together separate speech-to-text, language model, and text-to-speech APIs, Voice Agent Builder uses one interface on a speech-to-speech path built for Grok Voice, tightly coupled to the model rather than assembled from three different systems. Users can write a plain-language description of how calls should flow, attach documents, connect tools, set guardrails, and move quickly from zero to a working agent. It can retrieve from uploaded knowledge bases in common formats such as plain text, Markdown, Word, PowerPoint, Excel, HTML, JSON, and others.