# Alternatives to PolyAI > Source: https://theagentsindex.com/polyai/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 PolyAI:** - [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) - [Open models: yes — Open-weight models run two ways: ElevenLabs-hosted Qwen in the native model list, or Llama and Mixtral through a custom LLM endpoint such as Together AI, Groq or SambaNova.](https://elevenlabs.io/docs/eleven-agents/customization/llm/custom-llm/together-ai) **Trade-offs against PolyAI:** - [In your editor: no — The vendor enumerates its surfaces as web widgets, mobile apps, phone systems and custom integrations; no editor or IDE extension appears in that list.](https://elevenlabs.io/docs/eleven-agents/integrate/overview) - [Admin controls: partial — Guardrails constrain what an agent may say and per-tool approval constrains what it may do, but Guardrails is in Alpha and enabling MCP servers is not restricted to admins.](https://elevenlabs.io/docs/eleven-agents/best-practices/guardrails) - [Data residency: partial — US by default; EU, India and Singapore exist as separate Enterprise workspaces with their own accounts, API hosts and reduced model choice, and processing may still leave the region.](https://elevenlabs.io/docs/overview/administration/data-residency) [View ElevenLabs Agents](https://theagentsindex.com/elevenlabs-conversational-ai) ### 2. 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 PolyAI:** - [Multi-agent: yes — Squads route one conversation across several specialised assistants with context-preserving handoffs.](https://docs.vapi.ai/quickstart/introduction) - [Open models: yes — Open-weight models reach the pipeline through Groq, Together AI, Mistral, DeepSeek and OpenRouter, or a self-hosted server.](https://vapi.ai/platform) - [Self-hosted: partial — Self-serve is hosted only; on-premise is offered to large enterprises, and the orchestration layer otherwise never leaves Vapi.](https://docs.vapi.ai/faq) **Trade-offs against PolyAI:** - [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) - [In your pipeline: partial — Evals run as pipeline quality gates via API and CLI; there is no pull-request surface because there is no code to review.](https://docs.vapi.ai/observability/evals-quickstart) - [Data residency: partial — US is the default region; the EU region is frozen to existing accounts and new EU residency is enterprise-only, so regional control comes from your own buckets and models.](https://docs.vapi.ai/security-and-privacy/data-flow) [View Vapi](https://theagentsindex.com/vapi) ### 3. 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 PolyAI:** - [Self-hosted: partial — On-premise or VPC model deployment is sales-gated; separately, agent reasoning code can run on your own servers with Cartesia connecting to your URL.](https://www.cartesia.ai/pricing) - [Seat model: partial — Seats are not priced, but inviting anyone requires Startup ($49/mo) or above; a Free organization is capped at one member. The pricing page's 'unlimited workspace seats on every plan' contradicts this.](https://docs.cartesia.ai/enterprise/set-up-an-organization) - [Pooled budget: yes — Credits and prepaid agent dollars belong to the workspace, and every member shares the same resources and balance.](https://docs.cartesia.ai/enterprise/set-up-an-organization) **Trade-offs against PolyAI:** - [Writes code: no — The vendor positions itself as a voice model and voice agent lab; no surface authors application code.](https://docs.cartesia.ai/get-started/overview) - [Debugs and fixes: no — Its debugging surface is call logs for conversations, not diagnosis or repair of source code.](https://docs.cartesia.ai/line/introduction) - [Writes tests: no — The evaluations framework scores live calls against metrics you define; it produces no test code.](https://www.cartesia.ai/agents) [View Cartesia](https://theagentsindex.com/cartesia) ### 4. Bland Enterprise voice AI platform for inbound and outbound phone agents, running on Bland's own self-hosted models. **Research coverage:** 34/35 criteria **Where it improves on PolyAI:** - [Multi-agent: partial — Warm transfer runs a second proxy-agent leg alongside the primary agent, but that is call handoff, not general orchestration.](https://docs.bland.ai/platform/billing) - [Self-hosted: partial — VPC, on-premise and air-gapped deployments exist but the pricing table gates them to Enterprise contracts only.](https://www.bland.ai/product) - [Pooled budget: yes — Credits and limits sit on the organisation, so everyone with a key draws from one shared balance and one set of caps.](https://docs.bland.ai/platform/billing) **Trade-offs against PolyAI:** - [Writes code: no — Norm turns a plain-English description into a conversation pathway, persona, voice and tools; nothing on the site describes it authoring application source code.](https://www.bland.ai/product) - [Whole-codebase work: no — The unit of work is a pathway YAML directory synced to one Bland account via push, pull, diff and watch; there is no repository-wide code migration.](https://docs.bland.ai/sdks/cli) - [Claude: no — Claude never runs the call: Bland states no third-party AI provider is in the call path at all.](https://www.bland.ai/trust-security) [View Bland](https://theagentsindex.com/bland-ai) ### 5. AudioCodes Live Hub Self-service cloud platform for building voice AI agents and connecting them to real telephony channels. **Research coverage:** 33/35 criteria **Where it improves on PolyAI:** - [Multi-agent: yes — The AI Agents framework is explicitly multi-agent: several specialist agents collaborate on one call and callers are routed between them, with documented multi-agent topologies.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/AI%20Agents.htm) - [Seat model: partial — The platform itself is not sold per seat and imposes no user minimum; the only per-user charge is Microsoft Teams Direct Routing, billed monthly per enabled user.](https://www.audiocodes.com/livehub/pricing) - [Pooled budget: yes — Charges draw on a single account-level balance rather than per-user allowances, and the whole account is suspended when that shared balance reaches zero.](https://techdocs.audiocodes.com/livehub/Content/LiveHub/Account%20plans.htm) **Trade-offs against PolyAI:** - [Claude: partial — Claude models are supported only as bring-your-own custom models configured with your own Anthropic API key; the pre-deployed model list carries OpenAI and Google models only.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/Bring%20your%20own%20models.htm) - [In your editor: no — There is no editor or IDE extension: authoring happens in the web portal, and the only documented developer-tool integrations are the two MCP clients named below.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/MCP%20server.htm) - [On the command line: partial — AudioCodes ships no CLI of its own; terminal use is indirect, by pointing the Claude Code command-line agent at the platform's MCP endpoint with API client credentials.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/MCP%20server.htm) [View AudioCodes Live Hub](https://theagentsindex.com/audiocodes-live-hub) ### 6. Retell AI Pay-as-you-go platform for building, testing and running AI phone, chat and SMS agents. **Research coverage:** 34/35 criteria **Where it improves on PolyAI:** - [Multi-agent: yes — One call can be handed between several specialised AI agents mid-conversation, with the destination agent inheriting the full transcript, so work is split across agents rather than one monolith.](https://docs.retellai.com/build/conversation-flow/transfer-agent-node) - [Pooled budget: yes — A workspace holds one prepaid credit balance that every agent and member draws down in real time, and it blocks all new calls when it empties.](https://docs.retellai.com/accounts/billing) - [Getting out: yes — Filtered call and chat history exports to CSV including transcripts, and list/get APIs cover the same data; purchased credits never expire but are non-refundable once bought.](https://docs.retellai.com/features/session-history) **Trade-offs against PolyAI:** - [In your editor: partial — There is no editor plugin for building calls, but the hosted MCP server lets IDE-based assistants such as Cursor create, publish and inspect Retell agents from inside the editor.](https://docs.retellai.com/get-started/mcp-server) - [On the command line: no — The docs enumerate every way to drive Retell: dashboard, REST API, Node/Python SDKs and MCP server. No command-line tool is among them.](https://docs.retellai.com/general/introduction) - [Free tier: partial — You can sign up and run real calls without talking to sales, but the free allowance is a one-off $10 trial credit per email address rather than a standing free plan.](https://docs.retellai.com/accounts/billing) [View Retell AI](https://theagentsindex.com/retell-ai) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.