How Deepgram Voice Agent’s scores are calculated

The full audit trail, recomputed from the verdict data at build time through the same code that produced the leaderboard: verdict × quality × story weight per cell, cells sum to dimension scores, dimensions blend into the PA Score. Every number on the product page is reproducible from this page alone; for why the formula looks like this, see the methodology.

verdict factors: full ×1.0 · partial ×0.6 · disputed ×0.3 · none ×0.0 · n/a excluded from both sides · cell points = weight × quality × factor · cell max = weight × 10

PA Score26/100

Agent-ready 47.6 × 0.30 = 14.28

API quality 25.7 × 0.20 = 5.14

Openness 7.2 × 0.20 = 1.44

Built-in AI 17.8 × 0.15 = 2.67

Automation 13.5 × 0.15 = 2.02

(14.28 + 5.14 + 1.44 + 2.67 + 2.02) ÷ (0.30 + 0.20 + 0.20 + 0.15 + 0.15) = 25.55 ÷ 1.00 = 25.6

Scores are stored to 1 decimal; the product page’s pills round to whole numbers for display. Each dimension below shows the stories, verdicts, and cited evidence behind its number.

Agent-ready47.6/100×0.30 of the PA blend

Outside-in: can YOUR agent reach and drive this product — API, MCP, CLI, headless runs, agent docs.

Point an agent at llms.txt or agent-oriented docsweight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

[probe] https://developers.deepgram.com/llms.txt“PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown of any page, append `.md` to the page URL - For s”
[probe] https://developers.deepgram.com/docs/voice-agent.md“PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://develope”

Run the product headlessly / in CI for automationweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agent-architecture.md“Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive audio out.”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/getting-started.md“The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal.”
[claimed-docs] https://developers.deepgram.com/guides/fundamentals/token-based-authentication.md“Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services.”
[probe] https://developers.deepgram.com/developer-tools/cli/getting-started“official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”

Plug MCP servers into this product so it can use their toolsweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agents-function-calling.md“In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/mcp-server.md“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
[probe] https://developers.deepgram.com/developer-tools/agentic-tools“official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

Connect an agent via an official MCP serverweight 3

3 (weight) × 7 (quality) × 1.0 (full) = 21.0 of 30 max

[claimed-docs] https://developers.deepgram.com/developer-tools/cli/mcp-server.md“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
[probe] https://developers.deepgram.com/developer-tools/agentic-tools“official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/getting-started.md“The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal.”

Use an official CLIweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

[claimed-docs] https://developers.deepgram.com/developer-tools/cli/getting-started.md“The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal.”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/mcp-server.md“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
[probe] https://developers.deepgram.com/developer-tools/cli/getting-started“official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
[probe] https://developers.deepgram.com/developer-tools/agentic-tools“official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

Drive the product through a documented public APIweight 3

3 (weight) × 9 (quality) × 1.0 (full) = 27.0 of 30 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agent-architecture.md“Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive audio out.”
[probe] https://developers.deepgram.com/openapi.json“PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/getting-started.md“The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal.”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/mcp-server.md“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
[probe] https://developers.deepgram.com/developer-tools/cli/getting-started“official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
[claimed-docs] https://developers.deepgram.com/guides/fundamentals/token-based-authentication.md“Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services.”

Issue scoped/least-privilege API credentials for an agentweight 2

2 (weight) × 4 (quality) × 0.6 (partial) = 4.8 of 20 max

[claimed-docs] https://developers.deepgram.com/guides/fundamentals/token-based-authentication.md“Unlike traditional API keys, temporary tokens are ideal for real-time applications requiring secure, temporary access to Deepgram's services.”

Build against official SDKsweight 2

2 (weight) × 5 (quality) × 0.6 (partial) = 6.0 of 20 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agent.md“Browser Agent SDK: add voice AI to any web application via four composable packages.”
[probe] https://developers.deepgram.com/openapi.json“PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
[probe] https://developers.deepgram.com/developer-tools/cli/getting-started“official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”
[probe] https://developers.deepgram.com/developer-tools/agentic-tools“official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”

Subscribe to events via webhooksweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Agent-ready = 100.0 ÷ 210 × 100 = 47.6

API quality25.7/100×0.20 of the PA blend

The programmable surface once an agent is there — machine-readable spec, interactive docs, sandbox, versioning discipline.

Explore an interactive API reference with runnable examplesweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

[probe] https://developers.deepgram.com/openapi.json“PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
[probe] https://developers.deepgram.com/llms.txt“PROBE llms.txt: HTTP 200 at https://developers.deepgram.com/llms.txt # Deepgram's Docs ## Instructions for AI Agents - For clean Markdown of any page, append `.md` to the page URL - For s”
[probe] https://developers.deepgram.com/docs/voice-agent.md“PROBE docs-md: HTTP 200 at https://developers.deepgram.com/docs/voice-agent.md > For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://develope”

Download a machine-readable API spec (OpenAPI or equivalent)weight 2

2 (weight) × 9 (quality) × 1.0 (full) = 18.0 of 20 max

[probe] https://developers.deepgram.com/openapi.json“PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”

Test against a sandbox environment without touching production dataweight 1

1 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 10 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Rely on versioned APIs with a documented deprecation policyweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

API quality = 18.0 ÷ 70 × 100 = 25.7

Openness7.2/100×0.20 of the PA blend

Can you leave, inspect, or self-host — data export, open source, portability.

Do everything through the API that I can do in the UIweight 2

2 (weight) × 6 (quality) × 0.6 (partial) = 7.2 of 20 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agent-architecture.md“Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive audio out.”
[claimed-docs] https://developers.deepgram.com/docs/reusable-agent-configurations.md“Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created, you receive a UUID that can be passed in place of the full agent object”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/getting-started.md“The dg CLI lets you transcribe files, stream live audio, synthesize speech, analyze text, and manage your Deepgram account from the terminal.”
[claimed-docs] https://developers.deepgram.com/developer-tools/cli/mcp-server.md“The dg CLI includes a built-in MCP (Model Context Protocol) server that gives AI coding tools direct access to Deepgram APIs.”
[claimed-docs] https://developers.deepgram.com/docs/reusable-agent-configurations.md“A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no code deploy required.”
[probe] https://developers.deepgram.com/openapi.json“PROBE openapi: HTTP 200 at https://developers.deepgram.com/openapi.json — contains "openapi" key”
[probe] https://developers.deepgram.com/developer-tools/agentic-tools“official MCP server documented at https://developers.deepgram.com/developer-tools/agentic-tools”
[probe] https://developers.deepgram.com/developer-tools/cli/getting-started“official CLI documented at https://developers.deepgram.com/developer-tools/cli/getting-started”

Export all of my data in open formats and leaveweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Read the product's source under an open licenseweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Self-host the core productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agent-architecture.md“Deepgram's Voice Agent API collapses that stack into a single, unified API. You open one WebSocket connection, send audio in, and receive audio out.”
[claimed-docs] https://developers.deepgram.com/trust-security/data-privacy-compliance.md“For customers requiring data processing within the European Union, Deepgram provides an EU-specific endpoint at api.eu.deepgram.com.”

Openness = 7.2 ÷ 100 × 100 = 7.2

Built-in AI17.8/100×0.15 of the PA blend

Inside-out: how agentic the product itself is for its users — built-in assistants, autonomous features.

Get AI-generated insights and suggestions from my data inside the productweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Set up automations that run autonomously in the backgroundweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Delegate tasks to a built-in AI assistant inside the productweight 3

3 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 30 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Operate the product with natural-language commandsweight 2

2 (weight) × 8 (quality) × 1.0 (full) = 16.0 of 20 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agents-function-calling.md“In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
[claimed-docs] https://developers.deepgram.com/docs/voice-agent.md“Prompting: write system prompts that shape live-call behavior.”
[claimed-docs] https://developers.deepgram.com/docs/voice-agent-conversation-context.md“Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”
[claimed-docs] https://developers.deepgram.com/docs/voice-agent.md“Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”

Built-in AI = 16.0 ÷ 90 × 100 = 17.8

Automation13.5/100×0.15 of the PA blend

Depth of automation primitives — rules, scheduling, bulk operations, webhooks.

Perform bulk operations across many items at onceweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Define rules that trigger actions automatically on eventsweight 3

3 (weight) × 5 (quality) × 0.6 (partial) = 9.0 of 30 max

[claimed-docs] https://developers.deepgram.com/docs/voice-agents-function-calling.md“In the context of Deepgram Voice Agents, function calling enables your agent to perform tasks during a live conversation.”
[claimed-docs] https://developers.deepgram.com/docs/voice-agent.md“Multi-Agent Architecture: orchestrate multiple specialized agents that hand off based on context, intent, or domain.”
[claimed-docs] https://developers.deepgram.com/docs/voice-agent-conversation-context.md“Inject agent message | Mid-call | InjectAgentMessage | Makes the agent speak a specific line”

Schedule recurring jobs or workflowsweight 2

2 (weight) × 0 (quality) × 0.0 (none) = 0.0 of 20 max

no evidence cited — the verdict rests on absence of evidence, re-checked on refresh

Version, review, and roll back my automationsweight 1

1 (weight) × 3 (quality) × 0.6 (partial) = 1.8 of 10 max

[claimed-docs] https://developers.deepgram.com/docs/reusable-agent-configurations.md“Reusable Agent Configurations allow you to define and persist the agent block of your Settings message using the Deepgram API. Once created, you receive a UUID that can be passed in place of the full agent object”
[claimed-docs] https://developers.deepgram.com/docs/reusable-agent-configurations.md“A/B testing voices or prompts — Run two configurations in parallel and measure conversion, CSAT, or containment rate to pick a winner—no code deploy required.”

Automation = 10.8 ÷ 80 × 100 = 13.5