# Alternatives to HeyRik > Source: https://theagentsindex.com/heyrik/alternatives (current datasheets, evidence-ranked) Candidates share the baseline category or are previously researched peers. Requirements, preserved strengths, explicit trade-offs and research coverage decide the order; paid tier does not. ## Shortlist ### 1. ElevenLabs Agents Hosted platform for building voice and chat agents, with telephony, SDKs and a choice of LLM. **Research coverage:** 35/35 criteria **Where it improves on HeyRik:** - [Multi-agent: yes — An orchestrator agent routes a live conversation to specialist agents on natural-language conditions, and transfers can be nested; the transcript carries across.](https://elevenlabs.io/docs/eleven-agents/customization/tools/system-tools/agent-transfer) - [Agent permissions: yes — Tool use is gated per MCP server and per tool: always ask, fine-grained (auto-approved, requires approval, disabled), or no approval at all.](https://elevenlabs.io/docs/eleven-agents/customization/tools/mcp) - [Model choice: yes — You pick the model per agent, plus a backup cascade; LLM usage is billed on top of the plan and varies by model.](https://elevenlabs.io/docs/eleven-agents/customization/llm) **Trade-offs against HeyRik:** - No researched regression against the baseline. [View ElevenLabs Agents](https://theagentsindex.com/elevenlabs-conversational-ai) ### 2. Synthflow Enterprise voice AI platform with in-house telephony for inbound and outbound call automation. **Research coverage:** 35/35 criteria **Where it improves on HeyRik:** - [Multi-agent: yes — Subflows act as specialised agents that a parent flow triggers for individual tasks.](https://synthflow.ai/) - [Agent permissions: yes — Flow logic, approved knowledge sources, end-call reasons and handoff triggers bound what an agent may say or do.](https://synthflow.ai/) - [In your editor: partial — No Synthflow editor extension; Claude, Claude Code and Cowork can drive the workspace over MCP from where a developer already works.](https://docs.synthflow.ai/anthropic) **Trade-offs against HeyRik:** - No researched regression against the baseline. [View Synthflow](https://theagentsindex.com/synthflow-ai) ### 3. Vapi Developer platform for building, testing and deploying voice AI agents that make and receive phone calls. **Research coverage:** 35/35 criteria **Where it improves on HeyRik:** - [Multi-agent: yes — Squads route one conversation across several specialised assistants with context-preserving handoffs.](https://docs.vapi.ai/quickstart/introduction) - [Model choice: yes — You choose transcriber, LLM and voice independently and can swap any of them.](https://vapi.ai/platform) - [In your editor: partial — No agent runtime in the editor; `vapi mcp setup` teaches Cursor, Windsurf and VSCode the Vapi API so you can build from the IDE.](https://docs.vapi.ai/cli) **Trade-offs against HeyRik:** - [Opt out of training: partial — The privacy policy reserves call content for model training and names no toggle; the $1,000/month ZDR add-on is the only documented way to stop it being kept at all.](https://vapi.ai/privacy) [View Vapi](https://theagentsindex.com/vapi) ### 4. Retell AI Platform for building, testing and deploying AI voice and chat agents on phone, web and SMS, billed per minute. **Research coverage:** 34/35 criteria **Where it improves on HeyRik:** - [Multi-agent: yes — Agent Transfer (agent swap) hands a live call from one AI agent to another with full transcript inherited; subagent nodes attach tool-using agents inside a flow.](https://docs.retellai.com/build/conversation-flow/transfer-agent-node) - [Model choice: yes — You pick the LLM per agent from a published menu of 20+ models, each with its own per-minute rate, plus a fast tier and a custom-LLM escape hatch.](https://docs.retellai.com/build/single-multi-prompt/configure-basic-settings) - [In your editor: partial — Retell's own MCP server lets Cursor, Claude Desktop, Claude Code and Codex-style clients create, publish and inspect agents; the agent itself never runs in an editor.](https://docs.retellai.com/get-started/mcp-server) **Trade-offs against HeyRik:** - [Opt out of training: no — The privacy policy lists training its AI models among the uses of collected data, and its 'Your Choices' section offers only account deletion, cookie preferences, marketing opt-out and sale/sharing opt-out, with no training opt-out.](https://www.retellai.com/legal/privacy-policy) [View Retell AI](https://theagentsindex.com/retell-ai) ### 5. AudioCodes Live Hub Self-service SaaS for building voice AI agents and connecting them to SIP trunks, Teams, WhatsApp and WebRTC. **Research coverage:** 33/35 criteria **Where it improves on HeyRik:** - [Multi-agent: yes — Specialised agents exchange messages and split a call between them, with four documented orchestration modes and per-agent model choice.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/Multi-agent%20topologies.htm) - [Model choice: yes — You choose the LLM per agent and may substitute any supported provider with your own key, and equally bring a third-party conversational AI platform instead.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/Bring%20your%20own%20models.htm) - [On the command line: partial — AudioCodes ships no CLI of its own; the only terminal path is registering its MCP server with Claude Code, whose binary does the work.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/MCP%20server.htm) **Trade-offs against HeyRik:** - [Opt out of training: partial — AudioCodes never trains on customer data, but data you route to third-party AI providers falls under their policies and you must configure that yourself.](https://techdocs.audiocodes.com/livehub/Content/LiveHub/lh-data-handling.htm) [View AudioCodes Live Hub](https://theagentsindex.com/audiocodes-live-hub) ### 6. Cartesia Real-time speech models and a managed runtime for production phone and web voice agents. **Research coverage:** 35/35 criteria **Where it improves on HeyRik:** - [Model choice: yes — You pick the agent's LLM and can swap it in the Playground or API; Cartesia owns the speech models and manages the LLM integration.](https://docs.cartesia.ai/agents/models) - [In your editor: partial — No native IDE extension; the documented editor surface is the Cartesia MCP server used from Cursor or Claude Code.](https://docs.cartesia.ai/tools/ai/mcp) - [On the command line: yes — A `cartesia` CLI creates, deploys and manages agents, and can chat with agent logic locally.](https://docs.cartesia.ai/line/cli) **Trade-offs against HeyRik:** - [Done-for-you service: no — Self-serve software: you build and deploy the agent yourself; sales contact exists for Enterprise terms, not for building it for you.](https://www.cartesia.ai/agents) - [Opt out of training: partial — Opt-out is by request form for selected categories of content; Enterprise plans can additionally enable Zero Data Retention for TTS and STT inference.](https://www.cartesia.ai/legal/privacy) [View Cartesia](https://theagentsindex.com/cartesia) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.