# VoicEra

> VoicEra is an open-source, self-hosted platform for real-time phone agents combining STT, LLMs, TTS, and telephony in a Docker stack with 26+ AI providers.

- **Category:** AI Chat
- **Licence:** Apache-2.0
- **Latest version:** v3.1
- **Open source:** oss
- **Languages:** Typescript, Python
- **Tags:** Redis, No Code, Telephony, LLM, Open Source, Python, Docker Compose, Stt, Text To Speech, Minio, Self Hosted, Multi Tenant, Conversational Ai, Voice ai, Local llm, Ferretdb, Outbound Calls, Pipecat, Ai Calling, Inbound Calls, Open Source Voice Ai, Voice Ai Platform, On Prem Voice Agent Platform, Indian Languages, Language Ai, Voice Ai Agents

## Description

VoicEra lets operators run phone helplines, calling campaigns, and support lines without building voice infrastructure. The stack separates a control plane (API, dashboard, workers) from a real-time voice runtime. It uses FerretDB on PostgreSQL for data, MinIO for recordings, and Redis for queuing. The platform integrates 22 cloud AI vendors like OpenAI and Deepgram, plus Bhashini and Kenpath adapters for Indian languages, and two local providers for self-hosted models. Telephony works with Vobiz and Plivo. Multi-tenancy with roles is built in. Deployment uses a single Docker Compose file for evaluation, with production guidance for hardening, TLS, external stores, and scaling. Licensed Apache 2.0 by COSS-India.

## Links

- [Homepage](https://github.com/coss-india/voicera)
- [Website](https://voicera.mintlify.app/docs/guides)
- [Demo](https://sandbox.voicera.world)
- [GitHub Repository](https://github.com/COSS-India/VoicEra)

---
Source: https://selfhost.directory/project/voicera