# Alternatives to Leaping AI > Source: https://theagentsindex.com/leaping-ai/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 Leaping AI:** - [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 source: partial — The CLI and the client SDKs are public on GitHub and take contributions; the agent platform and the speech models themselves are proprietary and hosted.](https://elevenlabs.io/docs/eleven-agents/operate/cli) - [How it meters: yes — A monthly plan buys included call minutes and concurrency; overage is per minute, texts are per message, and LLM plus telephony are billed on top at usage.](https://elevenlabs.io/pricing/agents) **Trade-offs against Leaping AI:** - [Audit log: partial — OCSF-schema logs over 100 administrative endpoints, pullable into a SIEM, but gated on Enterprise tier plus an API key holding audit_log_read.](https://elevenlabs.io/docs/overview/administration/workspaces/audit-logs) - [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. PolyAI Enterprise platform for building voice and chat agents that resolve customer calls, priced per minute. **Research coverage:** 35/35 criteria **Where it improves on Leaping AI:** - [Open source: partial — The ADK CLI and Python package are Apache-2.0 in PolyAI's public repository; the platform, Agent Studio and the Raven model are proprietary.](https://github.com/PolyAI/adk) - [How it meters: yes — Metered by conversation volume, not seats: the MSA credits two CX Tokens per call minute and one per chat, with call time rounded up to 30-second increments.](https://poly.ai/pricing) - [Free tier: yes — Self-serve sign-up at Agent Studio needs no sales call, and trial use is free of charge but evaluation-only, with limits set at PolyAI's discretion.](https://poly.ai/trial-agreement) **Trade-offs against Leaping AI:** - [Self-hosted: no — Runs only as PolyAI-hosted SaaS on AWS with region-specific workspaces; no on-premise or customer-cloud deployment appears anywhere in the vendor's docs or security pages.](https://poly.ai/security) - [Audit log: partial — Permission-change audit logging is stated for Enterprise accounts only; every published version and change is separately kept as project history.](https://docs.poly.ai/user-management/introduction) [View PolyAI](https://theagentsindex.com/polyai) ### 3. 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 Leaping AI:** - [How it meters: yes — Metered per minute of voice, split into Retell voice infra ($0.055/min), the chosen LLM, TTS and telephony; chat agents meter per AI message; concurrency, numbers and knowledge bases bill monthly.](https://docs.retellai.com/accounts/billing) - [Free tier: yes — Self-serve signup with $10 of trial credit and full platform access, no call and no card required to start; the credit is granted once per email address.](https://www.retellai.com/pricing) - [API access: yes — REST API at api.retellai.com with bearer API keys, official Node and Python SDKs, and webhooks, all included on pay-as-you-go rather than gated to Enterprise.](https://docs.retellai.com/api-references/overview) **Trade-offs against Leaping AI:** - [Audit log: partial — Agent configuration changes are recorded as immutable published versions with browsable history and side-by-side comparison; no workspace-level log of administrative actions such as role changes or key rotation is documented.](https://docs.retellai.com/agent/version) - [Data residency: partial — Retell is US-based and runs on AWS with data primarily stored and processed in the United States, with SCCs for EEA/UK transfers; EU-resident processing is not offered, and on-prem deployment for residency requirements is an Enterprise path.](https://docs.retellai.com/general/compliance) [View Retell AI](https://theagentsindex.com/retell-ai) ### 4. 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 Leaping AI:** - [Open source: partial — The CLI and SDKs are MIT-licensed on Vapi's GitHub; the platform and its orchestration models are closed and hosted.](https://github.com/VapiAI/cli) - [How it meters: yes — Per call minute for Vapi hosting, plus model provider cost passed through at cost, plus $10 per concurrent line per month.](https://vapi.ai/pricing) - [Free tier: yes — Self-serve signup with a $5 credit grant and no card; it is a grant against usage, not a standing free tier.](https://vapi.ai/pricing) **Trade-offs against Leaping AI:** - [Audit log: partial — The dashboard keeps org-wide API, call and webhook logs and assistant version history; no member-action audit trail is documented.](https://docs.vapi.ai/debugging) - [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) - [Certifications: partial — SOC 2 Type II and a HIPAA BAA sit in the Scale contract, and the plan table shows SOC2 only in that column; HIPAA mode is a $2,000/month add-on on either plan.](https://docs.vapi.ai/enterprise/plans) [View Vapi](https://theagentsindex.com/vapi) ### 5. 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 Leaping AI:** - [Open source: partial — The official JS/TS and Python client SDKs are public repositories on Cartesia's GitHub; the Sonic and Ink models and the agent runtime are not.](https://docs.cartesia.ai/tools/client-libraries) - [How it meters: yes — Two meters: credits for the models (about 1 credit per TTS character, 3 credits per second of Ink-2 audio) and per-minute US dollars for agent calls.](https://docs.cartesia.ai/pricing) - [Free tier: yes — A $0/month plan with 20K credits and $1 of prepaid agent usage, signed up for without a call.](https://www.cartesia.ai/pricing) **Trade-offs against Leaping AI:** - [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) - [Audit log: partial — Deployment logs, call logs and transcripts are recorded per agent; no administrative audit trail of account actions is documented.](https://docs.cartesia.ai/line/infrastructure/observability) - [Data residency: partial — By default api.cartesia.ai routes to the nearest endpoint; pinned regional deployments (US, EU, UK, India, Australia) are Enterprise-only.](https://docs.cartesia.ai/enterprise/regional-endpoints) [View Cartesia](https://theagentsindex.com/cartesia) ### 6. Deepgram Voice Agent API One WebSocket API that runs speech-to-text, LLM orchestration and text-to-speech for real-time voice agents. **Research coverage:** 35/35 criteria **Where it improves on Leaping AI:** - [Open source: partial — The client SDKs are MIT-licensed on Deepgram's own GitHub, and the browser agent packages ship on npm; the Voice Agent runtime, the STT and TTS models and the self-hosted containers are proprietary and license-server validated.](https://github.com/deepgram/deepgram-js-sdk/blob/main/LICENSE) - [How it meters: yes — Metered per minute of WebSocket connection time, one rate covering STT, LLM and TTS together; the tier depends on which LLM you pick and whether you bring your own LLM or TTS. Billing is true per-second, not rounded up.](https://deepgram.com/pricing) - [API access: yes — The product is the API: one WebSocket at /v1/agent/converse, with official SDKs for JavaScript, .NET, Python, Go and Java, all marked GA.](https://developers.deepgram.com/docs/voice-agent-architecture) **Trade-offs against Leaping AI:** - [Done-for-you service: no — Self-serve software you build against: you sign up, get an API key and write the client. Enterprise brings an account representative and a contract, not a team that builds and runs the agent for you.](https://deepgram.com/product/voice-agent-api) - [Audit log: partial — Per-request logs (90 days in console, longer via the Usage API, with per-request USD cost) plus per-session message observability; no administrative-action audit trail is documented.](https://developers.deepgram.com/docs/using-logs-usage) - [Data residency: partial — EU and AU endpoints both serve the agent WebSocket, and Deepgram runs listen and speak in-region; managed LLM traffic is routed in-region only for OpenAI and Google in the EU, and on the AU endpoint the think step is processed outside Australia. Dedicated adds a customer-chosen AWS region.](https://developers.deepgram.com/reference/regional-endpoints) [View Deepgram Voice Agent API](https://theagentsindex.com/deepgram-voice-agent-api) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.