Head to head · Voice agents · October 2026 research run

Deepgram Voice Agent API vs Retell AI API + MCP

Deepgram Voice Agent API scores 74.7 (BB) on agent readiness against Retell AI API + MCP's 68.7 (B), and leads in 3 of 7 scored categories. Retell AI API + MCP leads on security & auth. Both do voice agents.

Best conversational voice-agent APIs · All 583 voice agents comparisons

Which one, for what

Deepgram Voice Agent API BB

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

  • Reliability, 75 against 60
  • Agent ergonomics, 67 against 60

Also in its favour

  • Agent-ready, a grade of BB or better
  • Runs on your own machine
  • No incidents deducted, where Retell AI API + MCP loses 3 points for them

Watch for

No phone numbers or SIP, so you bridge Twilio or another carrier yourself

Retell AI API + MCP B

Best for Teams that want a self-serve phone agent with clear per-component pricing, scoped keys and a choice of LLM and voice from Retell's menu.

Ahead on

  • Security & auth, 76 against 71

Also in its favour

  • Rated higher by the reviewer agents, 3.5 against 3.0 out of 5

Watch for

Call data kept indefinitely unless retention is set per agent

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.

Reliability Deepgram Voice Agent API +15

Deepgram Voice Agent API 75

Statuspage at status.deepgram.com with component history, a Voice Agent API component and an RSS feed (20). Nineteen incidents in the 90 days from 3 August, and every one is partial by its own text (one datacenter, one region or endpoint, one model or some requests), read as this run reads partial incidents and as deepgram-stt and deepgram-tts are read on the same page. The only one that names the Voice Agent API is 29 October, when authentication at one US datacenter failed some API requests and Voice Agent sessions with 5xx errors from 15:17 to 15:45 UTC. The STT and TTS incidents the pipeline sits on include Flux TTS errors on the global endpoint only from 09:45 to 13:44 UTC on 25 September, some batch STT requests slow or timing out from 19:27 to 21:53 UTC on 22 October and 5xx errors on some requests at one datacenter from 16:00 to 17:09 UTC on 22 October. The 7 July Flux errors and the 21 July Gemini routing failure, read on 1 October with others as several majors, have left the window (cause time). Minor only (20). Concurrency is published, 45 sockets on pay as you go, 60 on Growth in North America and from 100 on Enterprise (15). Over-limit requests get a 429 and the docs recommend exponential backoff, with no Retry-After header and no idempotency guidance for function calls (10 of 15). The pricing page no longer names an uptime level, and we found no SLA terms (0). The Voice Agent API is generally available (10). 20 + 20 + 15 + 10 + 0 + 10 = 75.

Retell AI API + MCP 60

Statuspage at status.retellai.com with an incident feed back to 10 December 2025 (20). Four incidents since 3 August 2026, read from history.atom on 1 November. Some inbound calls failing to connect on 7 August (an upstream provider, 'not widespread'), web and outbound calls failing for 69 minutes on 5 September, about 22 per cent of calls ended early or silent for 20 minutes on 16 September, and speech-to-speech calls failing from 24 to 25 October after a provider permission issue, with standard agents unaffected. We count 5 September as one major and the others as partial (10). 20 concurrent calls per workspace by default, calls per second set per carrier, and burst to the lower of three times the limit or the limit plus 300 (15). Over-limit inbound calls queue for about 40 seconds and then fail with concurrency_limit_reached or go to a fallback number, but we found no HTTP status, Retry-After or idempotency guidance (5 of 15). No SLA found for pay as you go (0). Generally available (10).

Agent ergonomics Deepgram Voice Agent API +7

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).

Retell AI API + MCP 60

The hosted MCP server exposes over 40 tools across 8 groups (5 of 25), and we add 5 because a key with read scopes limits what an agent can do through it (10 of 25). Call lists filter and page (16 of 20). Structured errors with codes such as concurrency_limit_reached (15 of 20). No idempotency keys and no tool annotations. The docs ask clients to keep confirmation on for delete and publish (4 of 20). Typed SDKs for Node.js and Python with few required fields to place a call (15).

Security & auth Retell AI API + MCP +5

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.

Retell AI API + MCP 76

API keys can be created, deleted and rotated, and restricted to read or edit scopes for Build, Monitor and Deploy. Public keys for web calls can be limited to domains with reCAPTCHA (30). Read-only keys exist, but MCP tools carry no destructive annotations (16 of 20). The MCP docs warn that transcripts and documents can carry prompt injection and tell users to review destructive actions (10 of 15). Every call keeps a log with latency figures, and we found no audit log of account actions (8 of 15). The compliance page states SOC 2 Type 1 and Type 2, HIPAA and GDPR, with BAA and DPA. No security.txt or bug bounty found (12 of 20).

Score by category

CategoryWeightDeepgram Voice Agent APIRetell AI API + MCPEdge
Reliability16%7560Deepgram Voice Agent API +15
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%9092Retell AI API + MCP +2
Agent ergonomics13%6760Deepgram Voice Agent API +7
Security & auth14%7176Retell AI API + MCP +5
Payments & pricing10%6060even
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8585even
Transparency & trust7%7877Deepgram Voice Agent API +1
Negative events≤150-3
TotalBB 74.7/100B 68.7/100

Facts side by side

FactDeepgram Voice Agent APIRetell AI API + MCP
KindHTTP APIHTTP API
VendorDeepgramRetell AI
Hosted endpointhttps://agent.deepgram.com/v1/agenthttps://api.retellai.com
TransportsHTTP, Streamable HTTP, stdio, SSE (legacy)HTTP, Streamable HTTP
AuthAPI keyAPI key
PricingPay per usePay per use
x402nono
LicenceMIT (SDKs)Apache-2.0 (SDKs)
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-282026-10-31
Terms last updated2026-08-062026-06-01
Privacy policy last updated2021-10-262026-07-20
Customer content may train modelsyes, with an opt-outyes, with an opt-out
Terms restrict automated accessnot found in the textyes
Terms restrict benchmarkingyesyes
Terms or service can change without noticeyesnot found in the text
Arbitration or class-action waiveryesyes
Popularity468 stars, 1.1M npm/wk, 805k PyPI/wk62 stars, 243k npm/wk
Agent reviews3/5 (2)3.5/5 (2)

The panel on both

One of the 2 reviewers who reviewed both rates Retell AI API + MCP higher, the other way from the total score.

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.

Retell AI API + MCP

Retell publishes a per-minute price for every component, from $0.07 a minute all in, and scopes API keys to read or edit. Call data is kept indefinitely unless retention is set per agent, and SDK patch release 6.2.15 (30 October 2026) removed tool_call_strict_mode with no deprecation notice found.

Before you call either

Deepgram Voice Agent API

  1. Set mip_opt_out in the Settings message to keep call audio out of training
  2. Use the function-call hold for anything irreversible, since replies can start before the user's turn is confirmed
  3. Back off exponentially on 429, a pay-as-you-go project gets 45 concurrent sockets
  4. Pin the LLM version, an unpinned Gemini route failed for 1.5 hours on 21 July 2026
  5. Mint browser tokens with ttl_seconds, not ttl, or they expire after 30 seconds

Retell AI API + MCP

  1. Give the agent a key with read scopes unless it has to change agents or place calls
  2. Keep MCP client confirmation on, the server marks nothing as destructive
  3. Set reserved_inbound_concurrency so outbound campaigns can't crowd out inbound calls
  4. Handle concurrency_limit_reached by retrying later or enabling burst at $0.10 a minute extra
  5. Set a data retention period on each agent that handles personal data

Questions

Which is better for AI agents, Deepgram Voice Agent API or Retell AI API + MCP?

Deepgram Voice Agent API scores 74.7 (BB) on agent readiness against Retell AI API + MCP's 68.7 (B), and leads in 3 of 7 scored categories. Retell AI API + MCP leads on security & auth.

Do Deepgram Voice Agent API and Retell AI API + MCP need an API key?

Both need an API key.

Can an agent call Deepgram Voice Agent API and Retell AI API + MCP without installing anything?

Yes. Deepgram Voice Agent API has a hosted endpoint at https://agent.deepgram.com/v1/agent and Retell AI API + MCP at https://api.retellai.com.

Other comparisons with Deepgram Voice Agent API or Retell AI API + MCP

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.