Rapida Voice
A self-hostable orchestration platform for real-time conversational voice systems, integrations, and observability.
- Source repo
- rapidaai/voice-ai
- Stars
- ★ 754
- Last updated
- today
- License
- NOASSERTION
- Primary language
- Go
- FA score
- 41/100 · Major gaps
At a glance
- How it runs
- Works with
- Universal · cross-platformOpenAI API · Claude API
- Cost
- Free software; you pay for model usage
- Setup effort
- High · needs real infrastructure
- You'll need
- Typical use
- An agency delivering white-label voice assistants that needs to retain customer credentials, branding, and infrastructure boundaries.
- Not a fit if
- Teams wanting only a hosted voice endpoint, not a multi-service stack to operate
- Commercial users needing branding removal or closed-source distribution
- Source review
- 41/100 · Major gaps 2 safety controls not found
What does this agent do, and when should you use it?
Rapida is an open-source, end-to-end voice AI orchestration platform written in Go for teams that want control over deployment, credentials, and branding. It uses gRPC for bidirectional communication and organizes real-time audio, STT, TTS, VAD, telephony, and multi-channel integrations. Its Docker Compose deployment includes a UI, nginx API Gateway, Web API, Assistant API, Endpoint API, and Integration API, with optional OpenSearch and Document API knowledge services. The stated platform scope also includes agent state management plus call logs, streaming events, tool traces, latency breakdowns, metrics, and dashboards. It is best suited to agencies and enterprise teams willing to operate and configure a multi-service voice stack, rather than buyers seeking only a hosted voice endpoint.
With make up-all, Rapida launches its UI, nginx API Gateway, Web API, Assistant API, Endpoint API, and Integration API. The platform streams real-time audio over gRPC and, according to its documented features, orchestrates STT, TTS, VAD, models, prompts, tools, and telephony channels; credentials for providers such as OpenAI, Anthropic, Deepgram, and Twilio are configured in service YAML files. It produces call logs, streaming events, tool traces, and latency data, and make up-all-with-knowledge additionally starts OpenSearch and the Document API. For extension work, the repository directs new STT/TTS providers to api/assistant-api/internal/transformer/ and new telephony channels to api/assistant-api/internal/telephony/.
- An agency delivering white-label voice assistants that needs to retain customer credentials, branding, and infrastructure boundaries.
- An enterprise platform team deploying a real-time voice system with a UI, gateway, and several API services for internal operations.
- A backend team that needs to configure OpenAI, Anthropic, or custom inference alongside its own models, prompts, and tools.
- A telephony automation team adding a voice channel, starting from
api/assistant-api/internal/telephony/. - An operations team investigating call latency or tool execution through call logs, streaming events, and tool traces.
How do you install or deploy this agent?
Prerequisites: Docker, Docker Compose, and 16GB+ RAM for all services. Run:
git clone https://github.com/rapidaai/voice-ai.git && cd voice-ai
make setup-local && make build-all
make up-allThen check the deployment with docker compose ps. The UI is available at http://localhost:3000; the nginx API Gateway is at http://localhost:8080. To include knowledge services, run make up-all-with-knowledge.
How do you use this agent?
After startup, edit the YAML configuration and add API keys for the chosen providers: docker/web-api/web.yml, docker/assistant-api/assistant.yml, docker/endpoint-api/endpoint.yml, docker/integration-api/integration.yml, and docker/document-api/config.yaml for knowledge services. The README explicitly gives OpenAI, Anthropic, Deepgram, and Twilio as credential examples. Use make logs-all for all logs, or make logs-web and make logs-assistant for individual services; rebuild changes with make rebuild-assistant or make rebuild-all. For a non-Docker run, use go mod download, go build -o bin/web ./cmd/web, and ./bin/web; PostgreSQL, Redis, and OpenSearch must be running separately.
What are this agent's strengths and limitations?
- The documented Go and gRPC design targets low-latency, bidirectional real-time audio communication.
- One deployment includes a UI, gateway, and multiple specialized API services rather than only a single voice component.
- It explicitly supports self-hosted or managed operation and lets teams select OpenAI, Anthropic, open-source models, or custom inference.
- Its observability scope is concrete: call logs, streaming events, tool traces, latency breakdowns, metrics, and dashboards.
- The full Docker service set requires Docker, Docker Compose, and at least 16GB of RAM.
- Teams must configure API keys in YAML for whichever model, speech, or telephony providers they choose.
- Non-Docker local operation requires separately running PostgreSQL, Redis, and OpenSearch.
- Licensing needs verification: repository metadata says
NOASSERTION, while the README claims GPL-2.0 with logo-retention conditions and describes a commercial license.
How does this agent compare with similar options?
The README positions Rapida against vendor lock-in by allowing OpenAI, Anthropic, open-source models, or custom inference; it does not name specific competing products.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Rapida Voice This agent | 41 · Major gaps | Self-hosted serviceFree + model costs | ★ 754 | today | Go | OpenAI API · Claude API |
| Bolna Voice AI Agent Platform | 56 · Major gaps | Self-hosted serviceFree + model costs | ★ 817 | today | Python | OpenAI API |
| Patter Voice SDK | 52 · Major gaps | Library / SDKFree + model costs | ★ 1.1k | 2mo ago | Python | OpenAI API · Claude API |
| Android Voice AI SDK (MVVM) | 47 · Major gaps | Library / SDKFree + model costs | ★ 2.6k | 5mo ago | Kotlin | Claude API |
How does FollowAgents rate this agent?
Why each dimension lost points
Evidence: README emphasizes self-hosting and ownership, but no specific least-privilege implementation details. API keys are configured (e.g., OpenAI, Anthropic), but key storage and access control are not described. Many dependencies, but no security audit or vulnerability scanning evidence. External effects include deployment to cloud marketplaces (AWS/GCP), but no user confirmation mechanism. Rollback mechanism not mentioned. Source attribution: clear copyright and contact info, but publisher unverified. Deductions: lack of user confirmation, rollback, and insufficient least-privilege evidence.
Evidence: README claims production-grade reliability, but no specific implementation details. Test files exist (e.g., auth_bridge tests), but not covering all services. Many dependencies, but no dependency availability guarantee. Failure messages: README provides some troubleshooting steps, but no detailed error message design. Deductions: dependency availability not proven, failure messages insufficient.
Evidence: README clearly targets agencies and enterprises with multiple scenarios, provides multiple deployment methods (Docker, local, cloud marketplaces). Capability boundaries: describes feature scope, but no explicit limits. Trigger precision: no specific trigger mechanisms. Environment fit: supports multiple clouds and local environments. Deductions: trigger precision insufficient, capability boundaries unclear.
Evidence: README provides clear architecture and quick start guide, detailed installation notes. Naming stability: no naming conventions provided. Examples and FAQ: quick start examples provided, but no FAQ. Known limitations: not explicitly listed. License: GPL-2.0 with additional terms, but license metadata is NOASSERTION. Versioning/changelog: not provided. Maintenance responsibility: contact emails provided, but no explicit maintenance policy. Deductions: missing naming stability, FAQ, known limitations, versioning/changelog.
Evidence: Output usability: UI and API endpoints provided, output formats clear. Marginal value: end-to-end voice orchestration platform with unique value. Cost-benefit: no cost information, but open-source license may reduce costs. Deductions: cost-benefit not quantified.
Evidence: Claim traceability: claims in README lack specific evidence. Cross-source corroboration: no external verification. Fact-inference separation: not clearly distinguished. Deductions: lack of verifiable evidence.
- Not found in source: confirmation before actingTurn on (or add) a confirmation step before it acts, and try it in a sandbox or test environment before real data.
- Not found in source: rollback or recovery pathBack up first, or work on a git branch or snapshot, so its changes can be undone.
- Publisher identity unverified; proceed with caution.
- License metadata is NOASSERTION; actual license is GPL-2.0 with additional terms; read carefully.
- Many dependencies without security audit evidence; assess supply chain risks yourself.
- No user confirmation or rollback mechanisms; evaluate risks before deployment.
Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
build-20261105-8005cca Pre-release
Release notes excerpt
Automated service packages for commit 8005cca636d0b721491fc658d1003f9395e3d62c.View on GitHub ↗ -
v3.0.0 v3.0.0 - Agentflow, AgentKit, Telephony, and Observability
-
v2.3.0 v2.3.0 - Bring Your Own LLM Infrastructure
FAQ
Can we self-host it and keep control of data and credentials?
Which third-party credentials are needed?
How do we enable knowledge services?
make up-all-with-knowledge; it includes OpenSearch and the Document API, which is listed at http://localhost:9010.How should startup failures be investigated?
make logs-all and docker compose ps; the README also provides a PostgreSQL connection test command.Does the documented licensing permit closed-source, unbranded use?
NOASSERTION license field should also be considered.