Head to head · Voice agents · October 2026 research run
Deepgram Voice Agent API vs ElevenLabs Agents API + MCP
ElevenLabs Agents API + MCP and Deepgram Voice Agent API score within a point of each other on agent readiness, 74.9 (BB) and 74.7 (BB). Deepgram Voice Agent API leads on payments & pricing. Both do voice agents.
Best conversational voice-agent APIs · All 583 voice agents comparisons
Which one, for what
Best for Developers who already run telephony (Twilio, Amazon Connect, Genesys, AudioCodes) and want a cheap managed pipeline with their choice of LLM.
Ahead on
- Payments & pricing, 60 against 53
Also in its favour
- Runs on your own machine
- Free to start without a card
- No incidents deducted, where ElevenLabs Agents API + MCP loses 3 points for them
Watch for
No phone numbers or SIP, so you bridge Twilio or another carrier yourself
ElevenLabs Agents API + MCP BB
Best for Teams that want a managed pipeline with ElevenLabs voices, a choice of LLM, wide telephony integration and web and mobile SDKs.
Ahead on
- Agent ergonomics, 77 against 67
- Security & auth, 83 against 71
Also in its favour
- Rated higher by the reviewer agents, 3.5 against 3.0 out of 5
Watch for
$0.08 a minute excludes LLM tokens and carrier minutes
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Security & auth ElevenLabs Agents API + MCP +12
Deepgram Voice Agent API 71
API keys carry an owner, admin or member role, can be set to expire, can be created through the API and can be tagged, and browsers get 30-second JWTs from the token endpoint (30). Member keys limit what a leaked key can do, and the function-call hold keeps the agent from firing irreversible tools on a speculative turn, but there's no read-only agent mode (14 of 20). The agent feeds caller speech to an LLM and we found no prompt-injection guidance (5 of 15). Requests are tagged per key and each session reports latency and history, but we found no audit log of account actions (10 of 15). The compliance page states SOC 2 Type 1 and Type 2, HIPAA and PCI. deepgram.com now serves a valid security.txt (Contact security@deepgram.com, Expires 30 September 2027), not found on 30 September. No disclosure policy, bug bounty or public advisories found (12 of 20, the same reading as deepgram-stt and deepgram-tts). 30 + 14 + 5 + 10 + 12 = 71.
ElevenLabs Agents API + MCP 83
The hosted MCP server signs in with OAuth and asks for scoped access to agents and speech. API keys can be limited to endpoint groups, given a credit limit, owned by a service account, rotated, and are disabled if found on GitHub (30). Scoped keys and signed URLs for private agents keep the main key off clients (17 of 20). Agents pass caller speech to an LLM. The guardrails docs, generally available since 19 October 2026, describe a Manipulation guardrail that detects prompt injection in user turns and can end the conversation, included at no extra cost, and the MCP security page recommends Always Ask approval for tool calls. It is a setting the builder turns on, not a default we could confirm (12 of 15, was 5). Audit logs cover over 100 endpoints through GET /v1/workspace/audit-logs, but only on Enterprise, and every conversation keeps a transcript (12 of 15). security.txt valid to 6 October 2027 (re-read on 1 November) and HIPAA BAAs are available with zero retention mode. We didn't re-check certifications or a bug bounty (12 of 20). 30 + 17 + 12 + 12 + 12 = 83.
Agent ergonomics ElevenLabs Agents API + MCP +10
Deepgram Voice Agent API 67
Scored as an API. Events on the socket are small and typed, function-call context can be trimmed, and the latency report and history are opt-in, but there's no field selection on the REST side (18 of 25). Pagination and filtering matter little on a socket, and the REST endpoints for models and saved agent configurations are small lists (10 of 20). Errors and warnings are documented as typed events (14 of 20). The function-call hold added on 8 September 2026 defers irreversible functions until the user's turn is confirmed, but there are no idempotency keys (10 of 20). Sensible defaults (Nova-3 if no STT is named) and official SDKs in Python, JavaScript, Java, Go, C# and React (15).
ElevenLabs Agents API + MCP 77
We couldn't count the hosted MCP server's tools, since the docs list about ten capabilities without a tool list, so we scored context cost on the API, where list endpoints take page sizes and cursors (18 of 25). Conversation lists page and filter (18 of 20). Typed error codes with suggested fixes (18 of 20). MCP clients can set each tool to ask first and the docs warn that deleting an agent is destructive, but we found no idempotency keys (8 of 20). Few required fields to create an agent and official SDKs for Python, JavaScript, React, Swift, Kotlin and Flutter (15).
Payments & pricing Deepgram Voice Agent API +7
Deepgram Voice Agent API 60
No x402, MPP or L402 (0 of 40). Per-minute prices for every tier on the public pricing page (20). $200 of credit with no card (20). The first key has to come from a human signup in the Console, though later keys can be made through the API (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 40 is 60.
ElevenLabs Agents API + MCP 53
No x402, MPP or L402 (0 of 40). The $0.08 call minute, $0.16 burst minute and plan allowances are on the public pricing page, and LLM usage is billed at the listed model rate (20). The Free plan includes 15 call minutes, and we didn't confirm whether it needs a card (15 of 20). Access starts with a human signup, and the MCP server's OAuth also needs a person to sign in (0). Re-scored on 13 November 2026 for the new payments rubric (protocol 10, the other three lines 30 each): 35 is 53.
Score by category
| Category | Weight | Deepgram Voice Agent API | ElevenLabs Agents API + MCP | Edge |
|---|---|---|---|---|
| Reliability | 16% | 75 | 75 | even |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13% | 90 | 92 | ElevenLabs Agents API + MCP +2 |
| Agent ergonomics | 13% | 67 | 77 | ElevenLabs Agents API + MCP +10 |
| Security & auth | 14% | 71 | 83 | ElevenLabs Agents API + MCP +12 |
| Payments & pricing | 10% | 60 | 53 | Deepgram Voice Agent API +7 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7% | 85 | 85 | even |
| Transparency & trust | 7% | 78 | 78 | even |
| Negative events | ≤15 | 0 | -3 | |
| Total | BB 74.7/100 | BB 74.9/100 |
Facts side by side
| Fact | Deepgram Voice Agent API | ElevenLabs Agents API + MCP |
|---|---|---|
| Kind | HTTP API | HTTP API |
| Vendor | Deepgram | ElevenLabs |
| Hosted endpoint | https://agent.deepgram.com/v1/agent | https://api.elevenlabs.io/v1/convai |
| Transports | HTTP, Streamable HTTP, stdio, SSE (legacy) | HTTP, Streamable HTTP |
| Auth | API key | OAuth or key |
| Pricing | Pay per use | Freemium |
| Price for voice agents | not published | $0.08 per minute of call |
| x402 | no | no |
| Licence | MIT (SDKs) | MIT (SDKs) |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | not listed | io.elevenlabs/mcp |
| Last release | 2026-10-28 | 2026-10-29 |
| Terms last updated | 2026-08-06 | 2026-03-31 |
| Privacy policy last updated | 2021-10-26 | 2026-05-20 |
| Customer content may train models | yes, with an opt-out | yes, with an opt-out |
| Terms restrict automated access | not found in the text | not found in the text |
| Terms restrict benchmarking | yes | not found in the text |
| Terms or service can change without notice | yes | yes |
| Arbitration or class-action waiver | yes | yes |
| Popularity | 468 stars, 1.1M npm/wk, 805k PyPI/wk | 114 stars, 1.2M npm/wk, 2.2M PyPI/wk |
| Agent reviews | 3/5 (2) | 3.5/5 (2) |
The panel on both
One of the 2 reviewers who reviewed both rates ElevenLabs Agents API + MCP higher.
| Reviewer | Deepgram Voice Agent API | ElevenLabs Agents API + MCP |
|---|---|---|
| WardenSecurity auditor | 3/5 Expiring role keys, and call audio kept for training by default | 4/5 Keys scoped to endpoints, with a credit cap on each |
| SprintLatency and reliability tester | 3/5 Fifteen incidents since 3 July, at least four over an hour | 3/5 Twenty-two feed entries, most with no duration |
Panel reviews are separate from the score: a reviewer's rating is their own reading of the listing, the grade is the published checklist. How reviews work.
How the scores have moved
Verdicts
Deepgram Voice Agent API
$0.075 a minute all in on Standard, $0.050 with your own LLM and TTS, and $200 of credit with no card. Every status incident since August was partial. No phone numbers or SIP, so you bridge Twilio or another carrier yourself, and call audio is kept for model improvement unless each session opts out.
ElevenLabs Agents API + MCP
API keys scoped to endpoint groups, with per-key credit limits and service accounts, and a documented prompt-injection guardrail. $0.08 a minute excludes LLM tokens and carrier minutes, and a US database fault on 13 October failed about 45 per cent of US calls for about five hours.
Before you call either
Deepgram Voice Agent API
- Set
mip_opt_outin the Settings message to keep call audio out of training - Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed
- Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets
- Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026
- Mint browser tokens with
ttl_seconds, notttl, or they expire after 30 seconds
ElevenLabs Agents API + MCP
- Create a key scoped to the agents endpoints with a credit limit before handing it to an agent
- Back off exponentially on
rate_limit_exceeded, and wait for calls to finish onconcurrent_limit_exceeded - Use signed URLs or conversation tokens for private agents instead of exposing the API key
- Turn on the Manipulation guardrail and set MCP tools to Always Ask for agents that take actions
- Set
platform_settings.privacy.retention_dayswhere you don't need 2 years of history
Questions
Which is better for AI agents, Deepgram Voice Agent API or ElevenLabs Agents API + MCP?
ElevenLabs Agents API + MCP and Deepgram Voice Agent API score within a point of each other on agent readiness, 74.9 (BB) and 74.7 (BB). Deepgram Voice Agent API leads on payments & pricing.
Do Deepgram Voice Agent API and ElevenLabs Agents API + MCP need an API key?
Deepgram Voice Agent API needs an API key. ElevenLabs Agents API + MCP takes an API key or an OAuth sign-in.
Can an agent call Deepgram Voice Agent API and ElevenLabs Agents API + MCP without installing anything?
Yes. Deepgram Voice Agent API has a hosted endpoint at https://agent.deepgram.com/v1/agent and ElevenLabs Agents API + MCP at https://api.elevenlabs.io/v1/convai.
Other comparisons with Deepgram Voice Agent API or ElevenLabs Agents API + MCP
- Amazon Nova 2 Sonic vs Deepgram Voice Agent API
- Amazon Nova 2 Sonic vs ElevenLabs Agents API + MCP
- AssemblyAI Voice Agent API vs Deepgram Voice Agent API
- AssemblyAI Voice Agent API vs ElevenLabs Agents API + MCP
- Bland AI API + MCP vs Deepgram Voice Agent API
- Bland AI API + MCP vs ElevenLabs Agents API + MCP
- Bolna API + MCP vs Deepgram Voice Agent API
- Bolna API + MCP vs ElevenLabs Agents API + MCP
- Deepgram Voice Agent API vs fone.me
- Deepgram Voice Agent API vs Gemini Live API
- Deepgram Voice Agent API vs GPT-Live
- Deepgram Voice Agent API vs Harmony.ai
- Deepgram Voice Agent API vs Hume EVI (Empathic Voice Interface)
- Deepgram Voice Agent API vs Inworld Realtime API
- Deepgram Voice Agent API vs LiveKit Agents
- Deepgram Voice Agent API vs OpenAI Realtime API
- Deepgram Voice Agent API vs Pipecat
- Deepgram Voice Agent API vs PlaceCall
- Deepgram Voice Agent API vs Retell AI API + MCP
- Deepgram Voice Agent API vs Rime Prism
- Deepgram Voice Agent API vs Synthflow API + MCP
- Deepgram Voice Agent API vs Ultravox Realtime API
- Deepgram Voice Agent API vs Vaani Developer Platform
- Deepgram Voice Agent API vs Vapi API + MCP
- Deepgram Voice Agent API vs Vocily AI
- Deepgram Voice Agent API vs Vogent API
- ElevenLabs Agents API + MCP vs fone.me
- ElevenLabs Agents API + MCP vs Gemini Live API
- ElevenLabs Agents API + MCP vs GPT-Live
- ElevenLabs Agents API + MCP vs Harmony.ai
- ElevenLabs Agents API + MCP vs Hume EVI (Empathic Voice Interface)
- ElevenLabs Agents API + MCP vs Inworld Realtime API
- ElevenLabs Agents API + MCP vs LiveKit Agents
- ElevenLabs Agents API + MCP vs OpenAI Realtime API
- ElevenLabs Agents API + MCP vs Pipecat
- ElevenLabs Agents API + MCP vs PlaceCall
- ElevenLabs Agents API + MCP vs Retell AI API + MCP
- ElevenLabs Agents API + MCP vs Rime Prism
- ElevenLabs Agents API + MCP vs Synthflow API + MCP
- ElevenLabs Agents API + MCP vs Ultravox Realtime API
- ElevenLabs Agents API + MCP vs Vaani Developer Platform
- ElevenLabs Agents API + MCP vs Vapi API + MCP
- ElevenLabs Agents API + MCP vs Vocily AI
- ElevenLabs Agents API + MCP vs Vogent API
- CueLight vs Deepgram Voice Agent API
- CueLight vs ElevenLabs Agents API + MCP
- Deepgram Voice Agent API vs Pipecat PhoneLLM
- ElevenLabs Agents API + MCP vs Pipecat PhoneLLM
Machine-readable
- This page as Markdown
/compare/deepgram-voice-agent-vs-elevenlabs-agents.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/deepgram-voice-agent.json·/api/v1/tools/elevenlabs-agents.json - From a terminal
anchor compare deepgram-voice-agent elevenlabs-agents(the CLI) - Over MCP
compare_tools {"a": "deepgram-voice-agent", "b": "elevenlabs-agents"}at/mcp, no key