03 / Scorecard / AI Platforms

Deepgram

Name: Deepgram Agent Readiness Scorecard
Item: Deepgram
Rating: 58
Author: Headless Index pipeline (auto)

Headless Index

58/100

denominator 60

JAIRF

69.3/100

AI-Aware

Verified

MAY 21, 2026

Methodology v1 · JAIRF v1.0.0

Editorial verdict

Deepgram is partially headless and partly UI-led. The Headless Index thesis-fit score of 58/100 puts it mid-table on the index, and JAIRF v1.0.0 puts it at 69.3/100 (Level 2, AI-Aware). In practice, vendors at this tier are partly machine-consumable: the core flows are reachable through code but several adjacent surfaces still expect a human at a dashboard, and the rest of this verdict explains where Deepgram lands inside that pattern. On the API surface, the question is whether the API is the product or a layer beneath the dashboard. Deepgram is the speech-to-text and audio-AI category leader. The REST + WebSocket API at api.deepgram.com exposes transcription (pre-recorded and streaming), text-to-speech (Aura), intelligence (summarization, topic detection), and project management. SDKs in Node, Python, .NET, Go, Rust, Java, and Swift. Published OpenAPI spec at developers.deepgram.com/openapi.json.^[1] Schema observability is the related test: can an agent introspect the contract from cold, or does it have to read prose documentation to do so? Public OpenAPI at developers.deepgram.com/openapi.json. Schema discoverability is reference-class for the audio-AI category.^[2] An agent can drive parts of this product, but not all of it: integrators should plan for human-in-the-loop checkpoints where the headless surface stops short. On headless operability: On headless operability, the docs crawl did not produce topic coverage sufficient to score programmatic setup, billing, teams, schema, or CLI workflows. A targeted AI review pass should visit the vendor's docs index and confirm what programmatic surfaces actually exist.^[3] On the MCP and agent-integration axis, which is the fastest-moving criterion in the index: Deepgram has been publicly forward on agent integration: Voice Agent API combines STT + LLM + TTS into one streaming endpoint, and the platform's documentation explicitly positions for voice-driven agent backends. No standalone MCP server yet, but the agent-product investment is substantial.^[4] Event posture closes the loop: an agent that cannot react to state changes is reduced to polling. On webhooks and events, the docs crawler did not locate a webhooks reference page or events catalog. Editorial review should confirm whether the vendor publishes events at all, and if so whether signing and replay are documented. Net assessment: integrators can build agent flows against Deepgram, but the rough edge to plan around is schema observability^[5]. Expect to wrap missing pieces in bespoke glue or accept human-in-the-loop checkpoints. Workable but requires scaffolding.

Verdict by Headless Index pipeline (auto)

// AI-drafted from the evidence layer. Editorial review pending.

Scores

Scorecard detail

Headless Index · 5 sub-criteria

API-first design intent15/20

scored

Deepgram is the speech-to-text and audio-AI category leader. The REST + WebSocket API at api.deepgram.com exposes transcription (pre-recorded and streaming), text-to-speech (Aura), intelligence (summarization, topic detection), and project management. SDKs in Node, Python, .NET, Go, Rust, Java, and Swift. Published OpenAPI spec at developers.deepgram.com/openapi.json.

signals (6)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPI specPublished, 0 operations
−GraphQL endpointNot discovered (5 probes; project-scoped endpoints require a real project ID)
+SDKs maintained13 (dotnet, go, java, javascript, python, rust, typescript); top by stars: deepgram/deepgram-python-sdk (431 stars)
+SDK recency9 of 13 SDK repos pushed within 30 days (most recent SDK commit: 2026-05-19)
+npm weekly downloads1.6M across published packages; top: @deepgram/sdk @ 541.0k/week

cite (5)

openapi.probes_tried@2026-05-20
graphql.probes_tried@2026-05-20
github.sdks@2026-05-20
freshness.most_recent_sdk_commit@2026-05-20
github.sdks@2026-05-20

Headless operationUnknown

Unknown

Projects, API keys, members, billing balance, usage, project requests, and model selection are all programmable. The Deepgram CLI plus SDK ecosystem cover the operational surface. Test mode plus self-host (Deepgram On-Prem) extend the deployment story.

signals (9)

+AI review appliedReviewer: Editorial review on 2026-05-20
−API operations exposedOpenAPI present but operations could not be counted
·Docs pages crawled0 pages (crawler: none)
·Auth schemes documentedAuth documentation page not reached by crawler
·Setup / quickstart docsNot reached by crawler
·Billing docsNot reached by crawler
·Teams / org docsNot reached by crawler
·CLI docsNot reached by crawler
·Schema / data model docsNot reached by crawler

cite (8)

openapi.operations_count@2026-05-20
docs.pages_crawled@2026-05-20
docs.pages_crawled@2026-05-20
docs.topics_found.setup@2026-05-20
docs.topics_found.billing@2026-05-20
docs.topics_found.teams@2026-05-20
docs.topics_found.cli@2026-05-20
docs.topics_found.schema@2026-05-20

MCP & agent posture15/20

scored

Deepgram has been publicly forward on agent integration: Voice Agent API combines STT + LLM + TTS into one streaming endpoint, and the platform's documentation explicitly positions for voice-driven agent backends. No standalone MCP server yet, but the agent-product investment is substantial.

signals (4)

+AI review appliedReviewer: Editorial review on 2026-05-20
+Official MCP serverhttps://github.com/deepgram/cli (5 stars, last commit 7 days ago)
·Community MCP servers1 community MCP repos; top by stars: https://github.com/deepgram/mcp (1 stars)
+Agent-friendly SDKs3 TS/JS SDKs available; top: @deepgram/sdk (541.0k/week downloads)

cite (3)

mcp.official_server.url@2026-05-20
mcp.community_servers[0].url@2026-05-20
github.sdks@2026-05-20

Schema observability5/20

scored

Public OpenAPI at developers.deepgram.com/openapi.json. Schema discoverability is reference-class for the audio-AI category.

signals (3)

+AI review appliedReviewer: Editorial review on 2026-05-20
+OpenAPIPublished at https://developers.deepgram.com/openapi.json (OpenAPI undefined, 0 operations)
−GraphQL introspectionNo GraphQL endpoint discovered (5 probes; some vendors use project-scoped endpoints that require a real project handle)

cite (2)

openapi.probes_tried@2026-05-20
graphql.probes_tried@2026-05-20

Webhooks & eventsUnknown

Unknown

Deepgram webhook callbacks for completed pre-recorded transcriptions with HMAC signing. Catalog is purpose-built for asynchronous transcription pipelines.

signals (2)

+AI review appliedReviewer: Editorial review on 2026-05-20
·Webhook docs pageNot reached by crawler within budget (0 pages crawled). Cannot confirm whether vendor offers webhooks.

cite (1)

docs.pages_crawled@2026-05-20

JAIRF · 6 dimensions

FCFoundational Compliance

55/100

Structural validity, standards conformance, and parsability of the OpenAPI specification.

DXJDeveloper Experience & Tooling Compatibility

80.8/100

Documentation clarity, example coverage, response completeness, and ingestion health.

ARAXAI-Readiness & Agent Experience

88.1/100

Semantic clarity, intent expression, datatype specificity, and error standardization.

AUAgent Usability

80/100

Operational composability, complexity comfort, navigation affordances, and safety patterns.

SECSecurity

50/100

Authentication strength, transport security, secret hygiene, and OWASP risk posture.

AIDAI Discoverability

50.7/100

Descriptive richness, intent phrasing, workflow context, and registry signals.

Band rationale:C band: scores 40-75 range

04 / Embed

Show Deepgram's score on your site.

Drop a live badge into your README, footer, or marketing page. It updates automatically when we re-score, and every embed is a dofollow link back here.

Get embed code

Calibration

How THI compares to external scorers

Source	Score	Measures	Last checked
Fern Agent Score	not found	Documentation completeness and SDK shape (~22 checks)	—
CLIRank Agent Friendliness	76 · Good	CLI readiness, docs quality, and overall agent affordances	—
Cloudflare Is It Agent Ready?	blocked	Cloudflare's manual agent-readiness heuristic per vendor URL	—
Jentic Scorecard	n a	JAIRF-based scorecard requiring a public OpenAPI specification	—

THI 58 vs external median 76, delta -18

THI display 58 vs external median 76 (delta -18). Within calibration band.

Peers in AI Platforms

E2BB

Headless Index 60/100

BasetenC

Headless Index 56/100

RunPodC

Headless Index 54/100

See full AI Platforms ranking →