# Alternatives to Deepgram Voice Agent API > Source: https://theagentsindex.com/deepgram-voice-agent-api/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 Deepgram Voice Agent API:** - [Done-for-you service: partial — Self-serve software you run, but enterprises can buy ElevenLabs Forward Deployed Engineers who scope, build and stabilise the deployment; no price is published.](https://elevenlabs.io/agents/forward-deployed-engineers) - [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) **Trade-offs against Deepgram Voice Agent API:** - No researched regression against the baseline. [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 Deepgram Voice Agent API:** - [Done-for-you service: partial — You build and run the agent yourself; the Scale contract adds an embedded Vapi engineer for the go-live, not a done-for-you build.](https://vapi.ai/) - [Multi-agent: yes — Squads route one conversation across several specialised assistants with context-preserving handoffs.](https://docs.vapi.ai/quickstart/introduction) - [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 Deepgram Voice Agent API:** - [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) - [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) ### 3. LiveKit Agents Open-source Python and Node.js framework for voice AI agents, with LiveKit Cloud hosting, telephony and observability. **Research coverage:** 35/35 criteria **Where it improves on Deepgram Voice Agent API:** - [Multi-agent: yes — Multiple agents in one session via handoffs, plus a supervisor pattern where one agent keeps control and delegates to scoped tasks.](https://docs.livekit.io/agents/logic/workflows.md) - [On the command line: yes — The lk CLI creates projects, deploys agents and manages LiveKit Cloud; agents can also be run and talked to locally in console mode.](https://docs.livekit.io/reference/developer-tools/livekit-cli.md) - [Self-hosted: yes — Agents are containers you can run on your own Kubernetes; the LiveKit media server and SIP service are separately self-hostable. Self-hosted agents still meter WebRTC participant minutes if they connect to LiveKit Cloud.](https://docs.livekit.io/deploy/custom/deployments.md) **Trade-offs against Deepgram Voice Agent API:** - [Bring your own key: partial — Provider plugins run on your own account, key and billing, and self-hosted agents run in your own cloud. Bringing your own key to traffic routed through LiveKit Inference is not supported.](https://docs.livekit.io/agents/models/llm/) - [Pooled budget: partial — No per-user balances: allowances pool inside a project. Sharing one plan across projects, and quotas managed at workspace level, are Enterprise only.](https://docs.livekit.io/deploy/admin/quotas-and-limits.md) - [Certifications: partial — SOC 2 Type II active, GDPR and CCPA/CPRA compliant, EU-US DPF certified; ISO 27001 and PCI DSS still in progress, HIPAA BAAs only for Scale and Enterprise, and the security reports row is Scale and above.](https://livekit.com/security) [View LiveKit Agents](https://theagentsindex.com/livekit-agents) ### 4. Telnyx Voice AI Agents Carrier-owned platform for phone and web voice agents, with telephony, STT, TTS, LLM and orchestration in one stack. **Research coverage:** 35/35 criteria **Where it improves on Deepgram Voice Agent API:** - [Multi-agent: yes — A handoff tool passes one live conversation between specialist assistants sharing context, and remote A2A agents plus multi-participant calls extend that beyond a single Telnyx assistant.](https://developers.telnyx.com/docs/inference/ai-assistants/no-code-voice-assistant) - [In your editor: partial — The agent itself never runs in an editor, but Telnyx ships an MCP server that lets IDE assistants such as Cursor or Windsurf create and manage Telnyx AI assistants from the editor.](https://developers.telnyx.com/docs/development/mcp/local-mcp) - [On the command line: yes — Two terminal surfaces exist: a full resource-level Telnyx CLI and an Agent CLI whose composite commands stand up an assistant on a phone number in one invocation.](https://developers.telnyx.com/docs/development/cli/agent-cli) **Trade-offs against Deepgram Voice Agent API:** - [GPT: partial — GPT models run as an external provider you supply credentials for: you create an OpenAI API key, store it as an integration secret and select the model, and OpenAI free-plan keys are rejected outright.](https://developers.telnyx.com/docs/inference/data-residency) - [Self-hosted: no — The runtime, telephony and portal stay on Telnyx; only the LLM and TTS steps can be pointed at your own endpoint, and Enterprise 'dedicated infrastructure' is still Telnyx-operated.](https://developers.telnyx.com/docs/inference/ai-assistants/no-code-voice-assistant) - [Open source: no — The platform is proprietary: Telnyx keeps title to the AI Services and underlying models. Public repositories exist only for client-side SDKs, the CLI and the local MCP server.](https://telnyx.com/legal/ai-services-terms) [View Telnyx Voice AI Agents](https://theagentsindex.com/telnyx-voice-ai) ### 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 Deepgram Voice Agent API:** - [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) - [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 Deepgram Voice Agent API:** - [Multi-agent: no — System tools enumerate three slots: end call, DTMF, and transfer to an E.164 phone number. An agent therefore hands off to a number, not to another Cartesia agent.](https://docs.cartesia.ai/agents/system-tools) - [Open models: partial — The LLM layer routes through LiteLLM to 100+ providers, but the vendor names only Anthropic, OpenAI and Google, and its own speech models are API-only.](https://docs.cartesia.ai/line/sdk/agents) - [Bring your own key: partial — No bring-your-own LLM key: Cartesia bills the LLM itself. You can bring your own carrier via SIP trunking and host the agent's reasoning code yourself.](https://docs.cartesia.ai/agents/models) [View Cartesia](https://theagentsindex.com/cartesia) ### 6. 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 Deepgram Voice Agent API:** - [Done-for-you service: partial — The product itself is self-service software you run, but AudioCodes sells support packages and professional-services hours as purchasable add-ons for onboarding and integration work.](https://www.audiocodes.com/livehub) - [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) - [MCP server: yes — The AI Agents service exposes its own MCP server over streamable HTTP so another agent can create agents, run test suites and inspect conversations, with an optional read-only mode.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/MCP%20server.htm) **Trade-offs against Deepgram Voice Agent API:** - [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) - [Open models: partial — Open-weight models such as gpt-oss and Gemma are reachable only through the bring-your-own-model path with your own Groq, Cerebras or OpenAI keys, not from the pre-deployed set.](https://techdocs.audiocodes.com/livehub/Content/AI-Agents/Bring%20your%20own%20models.htm) - [Self-hosted: no — Live Hub is a vendor-operated SaaS running in AudioCodes' own Azure deployments; the only customer choice is which of four regions holds the data, not whose infrastructure runs it.](https://techdocs.audiocodes.com/livehub/Content/LiveHub/Global%20region%20support.htm) [View AudioCodes Live Hub](https://theagentsindex.com/audiocodes-live-hub) ## Method Unknown data is never treated as a benefit or a trade-off. Featured placement is labelled but cannot alter recommendation order.