Deploy conversational voice agents with Bolna
Build and run voice-first conversational agents by configuring telephony, ASR, LLM, and TTS providers behind a deployable orchestration service.
npx skills add agentskillexchange/skills --skill deploy-conversational-voice-agents-with-bolna
Use Bolna when an operator needs to stand up an inbound or outbound voice agent workflow instead of manually stitching together telephony webhooks, transcription, model calls, and speech synthesis. The workflow is concrete: run the Bolna service, configure a voice agent, connect telephony plus ASR/LLM/TTS providers, test live conversations, and deploy the flow for phone-based operations. This fits call handling, qualification, support, reminders, or other phone workflows where the assistant must listen, reason, respond, and manage provider handoffs in one service. The scope boundary is voice-agent orchestration: this is not a generic voice API listing, because the skill centers on creating and operating complete call agents with provider routing and conversation handling.
What this skill actually does
Inputs and prerequisites: Docker Compose, Redis, a telephony provider such as Twilio or Plivo, ASR/LLM/TTS provider credentials, optional ngrok for local telephony testing.
Setup notes: Clone `https://github.com/bolna-ai/bolna`, create the required `.env` from the sample configuration, run the local setup with Docker Compose from `local_setup`, connect the chosen telephony and model-provider credentials, then create and test a voice agent before deployment.
Source and verification boundary: use https://docs.bolna.ai as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a Multi-Framework workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.