Artificial intelligence · llms.txt file breakdown
Deepgram's Docs organizes Deepgram content, including Instructions for AI Agents, Docs, API Docs, OpenAPI Specification and 1 additional sections.
The actual file
The saved llms.txt text, displayed as source. The file belongs to its publisher; the live endpoint may change.
Showing the first 18000 characters. Load the complete file to read the remainder.
# Deepgram's Docs
## Instructions for AI Agents
- For clean Markdown of any page, append `.md` to the page URL
- For section-specific indexes, append `/llms.txt` to any section URL
- For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://developers.deepgram.com/_mcp/server
## Docs
- [Welcome to Deepgram's Docs!](https://developers.deepgram.com/home.md): Deepgram developer documentation — APIs, SDKs, and tools for speech-to-text, text-to-speech, voice agents, and audio intelligence.
- [Ask AI](https://developers.deepgram.com/ask-ai.md): Get instant answers about Deepgram's products, APIs, and documentation
- [Support](https://developers.deepgram.com/support.md): Every way to get help with Deepgram, starting with the fastest.
- [Changelog](https://developers.deepgram.com/changelog/llms.txt)
- [Deepgram CLI — Getting Started](https://developers.deepgram.com/developer-tools/cli/getting-started.md): Transcribe audio, synthesize speech, and manage your Deepgram account — all from your terminal.
- [CLI Installation](https://developers.deepgram.com/developer-tools/cli/installation.md): Install the Deepgram CLI on macOS, Linux, and Windows.
- [CLI Authentication](https://developers.deepgram.com/developer-tools/cli/authentication.md): Authenticate the Deepgram CLI with your API key.
- [Speech-to-Text Commands](https://developers.deepgram.com/developer-tools/cli/speech-to-text.md): Transcribe audio files, URLs, microphone, and stdin with the dg CLI.
- [Text-to-Speech Commands](https://developers.deepgram.com/developer-tools/cli/text-to-speech.md): Synthesize speech from text with Deepgram Flux TTS and Aura models using the dg CLI.
- [Text Intelligence Commands](https://developers.deepgram.com/developer-tools/cli/text-intelligence.md): Analyze text for sentiment, topics, summaries, and intents using the dg CLI.
- [Account Management Commands](https://developers.deepgram.com/developer-tools/cli/account-management.md): Manage projects, API keys, team members, and usage with the dg CLI.
- [MCP Server](https://developers.deepgram.com/developer-tools/cli/mcp-server.md): Use the Deepgram CLI as an MCP server for AI coding tools.
- [Shell Completion](https://developers.deepgram.com/developer-tools/cli/shell-completion.md): Enable tab completion for bash, zsh, and fish shells.
- [Plugin System](https://developers.deepgram.com/developer-tools/cli/plugins.md): Extend the Deepgram CLI with community-built plugins.
- [Agentic developer tools](https://developers.deepgram.com/developer-tools/agentic-tools.md): Deepgram CLI, MCP servers, and agent skills — give your AI coding tools built-in knowledge of Deepgram APIs, docs, and starter apps.
- [Your Data at Deepgram](https://developers.deepgram.com/trust-security/your-data.md): How Deepgram handles your audio, text, and transcripts: what we store, how long we keep it, where it is processed, and the controls you have over each.
- [Security Policy](https://developers.deepgram.com/trust-security/security-policy.md): Learn about Deepgram's commitment to maintaining a company culture that values information security and data privacy
- [Data Privacy Compliance](https://developers.deepgram.com/trust-security/data-privacy-compliance.md): Learn about Deepgram data privacy compliance frameworks and certifications.
- [Information Security & Privacy Statement](https://developers.deepgram.com/trust-security/information-security-privacy.md): Review Deepgram's information security and privacy statement.
- [SDK Feature Matrix](https://developers.deepgram.com/sdks/sdk-features.md): A matrix of all Deepgram API features supported by our different SDKs.
- [Make Your First API Request](https://developers.deepgram.com/guides/fundamentals/make-your-first-api-request.md): Follow these steps to get started with Deepgram and make your first request.
- [Authenticating](https://developers.deepgram.com/guides/fundamentals/authenticating.md): Learn how to authenticate with Deepgram's API.
- [Token-Based Auth](https://developers.deepgram.com/guides/fundamentals/token-based-authentication.md): Generates a temporary JSON Web Token (JWT) with a 30-second TTL (Time To Live) for Deepgram APIs.
- [Model Metadata](https://developers.deepgram.com/guides/fundamentals/model-metadata.md): Use the Models endpoint to determine which models you can access and returns metadata about those models.
- [Using Custom Add On Parameters with SDKs](https://developers.deepgram.com/guides/fundamentals/using-custom-parameters-sdks.md): Learn how to use custom add on parameters to set arbitrary key/value pairs with the Deepgram SDKs.
- [Tagging Your Usage Data](https://developers.deepgram.com/guides/fundamentals/tagging-your-usage-data.md): Tagging allows you to label your requests for grouping & filtering usage reports.
- [Managing Projects](https://developers.deepgram.com/guides/deep-dives/managing-projects.md): Learn about Deepgram Projects, which organize all of your Deepgram resources and consist of a set of users, a set of API Keys, and billing and monitoring settings.
- [Using Multiple Projects](https://developers.deepgram.com/guides/deep-dives/using-multiple-projects.md): Learn about scenarios in which it would be best to set up multiple Deepgram projects.
- [Working With Roles & API Scopes](https://developers.deepgram.com/guides/deep-dives/working-with-roles.md): Learn how to use roles and API scope permissions when working with the Deepgram API and Console.
- [Supported Audio Formats](https://developers.deepgram.com/docs/supported-audio-formats.md): Learn about audio formats and encoding supported by Deepgram.
- [Deployment Options](https://developers.deepgram.com/docs/deployment-options.md): Learn about the deployment options available for Deepgram services.
- [Creating API Keys](https://developers.deepgram.com/docs/create-additional-api-keys.md): Learn about the fundamentals of creating API keys with the Deepgram Console or the Deepgram API.
- [Safely Removing Team Members With Active API Keys](https://developers.deepgram.com/guides/deep-dives/safely-removing-team-members-with-active-api-keys.md): Learn how to offboard team members without disrupting production services that rely on their API keys.
- [Using the Sec-WebSocket-Protocol](https://developers.deepgram.com/docs/using-the-sec-websocket-protocol.md): Learn how to to use the Sec-WebSocket-Protocol with Deepgram APIs to send secure client side requests via web sockets.
- [Logs & Usage Data](https://developers.deepgram.com/docs/using-logs-usage.md): Learn how to use Deepgram's Log and Usage features.
- [Model Improvement Partnership Program](https://developers.deepgram.com/docs/the-deepgram-model-improvement-partnership-program.md): Learn about how Deepgram trains our AI models and how you can opt out of our Model Improvement Program.
- [Working With Concurrency Rate Limits](https://developers.deepgram.com/docs/working-with-concurrency-rate-limits.md): Learn how to better handle concurrency rate limit issues when using Deepgram.
- [Audio Preprocessing & Barge-In](https://developers.deepgram.com/guides/deep-dives/audio-preprocessing-barge-in.md): When noise suppression and echo cancellation help speech-to-text — and when they hurt.
- [Understanding NAT Port Exhaustion](https://developers.deepgram.com/docs/understanding-nat-port-exhaustion.md): Learn how NAT port exhaustion causes intermittent connection failures and how to diagnose and resolve it in your environment.
- [Build a Voice Agent with Pipecat and Deepgram](https://developers.deepgram.com/docs/build-voice-agent-with-pipecat-and-deepgram.md): Build a real-time voice agent with Pipecat for pipeline orchestration, Deepgram Nova-3 for speech-to-text, and Deepgram Aura for text-to-speech.
- [Build a Voice Agent with LiveKit and Deepgram](https://developers.deepgram.com/docs/build-voice-agent-with-livekit-and-deepgram.md): Build a real-time voice agent with LiveKit for WebRTC transport, Deepgram Nova-3 for speech-to-text, and Deepgram Aura for text-to-speech.
- [Calculate Talk Time Analytics](https://developers.deepgram.com/docs/calculate-talk-time-analytics.md): Using Deepgram's speech-to-text API with diarization, you can gather the data you need to make informed decisions about your organization's interactions.
- [Amazon Connect and Deepgram](https://developers.deepgram.com/docs/deepgram-with-amazon-connect.md): Integrate Deepgram's Speech-to-Text (STT) and Text-to-Speech (TTS) models directly into Amazon Connect and Amazon Lex to power intelligent IVR systems and virtual voice agents.
- [AWS S3 Presigned URLs and Deepgram](https://developers.deepgram.com/docs/using-aws-s3-presigned-urls-with-the-deepgram-api.md): Use S3 to send audio data to Deepgram and store transcripts from Deepgram directly in S3.
- [AudioCodes (LiveHub) and Deepgram STT](https://developers.deepgram.com/docs/integrate-deepgram-stt-with-audiocodes.md): Learn how to integrate Deepgram STT with AudioCodes (LiveHub).
- [Genesys and Deepgram](https://developers.deepgram.com/docs/genesys-deepgram.md): Genesys is a cloud-based platform used by many organizations to manage their call centers. With our plug-and-play Genesys integration, you can have all of your Genesys calls transcribed by Deepgram.
- [LiveKit and Deepgram](https://developers.deepgram.com/docs/livekit-integration.md): Build a real-time voice AI agent using LiveKit Agents with Deepgram speech-to-text and text-to-speech.
- [Google Dialogflow CX and Deepgram](https://developers.deepgram.com/docs/use-deepgram-with-dialogflow-cx.md): Dialogflow CX is a framework for building virtual agents. Learn how to incorporate Deepgram's transcription and text-to-speech for improved accuracy.
- [Make.com and Deepgram](https://developers.deepgram.com/docs/makecom-deepgram-integration.md): Learn how to use Deepgram in Make.com workflows.
- [Pipecat and Deepgram](https://developers.deepgram.com/docs/pipecat-integration.md): Build a real-time voice AI agent using Pipecat with Deepgram speech-to-text and text-to-speech.
- [Twilio and Deepgram STT](https://developers.deepgram.com/docs/twilio-and-deepgram-stt.md): Transcribe a live phone call in real time with Twilio and Deepgram.
- [Twilio and Deepgram TTS](https://developers.deepgram.com/docs/twilio-and-deepgram-tts.md): Stream real-time speech generated by Deepgram Flux TTS into a live Twilio phone call.
- [Zapier and Deepgram](https://developers.deepgram.com/docs/zapier-integration.md): Learn how to use Deepgram in Zapier automated workflows.
- [Zoom and Deepgram](https://developers.deepgram.com/docs/integrate-deepgram-with-zoom.md): Learn how to transcribe Zoom meetings using Deepgram.
- [Deepgram API Overview](https://developers.deepgram.com/reference/deepgram-api-overview.md): Overview of all Deepgram REST and WebSocket APIs — voice agents, speech-to-text, text-to-speech, audio intelligence, text intelligence, and account management.
- [Authentication](https://developers.deepgram.com/reference/authentication.md): Authenticating requests made to the Deepgram API
- [Regional Endpoints](https://developers.deepgram.com/reference/regional-endpoints.md): Use Deepgram's regional endpoints to keep data processing within specific geographic regions.
- [Configuring Custom Endpoints](https://developers.deepgram.com/reference/custom-endpoints.md): Instructions for using Deepgram's regional, Dedicated, and self-hosted endpoints with your applications.
- [Errors](https://developers.deepgram.com/docs/errors.md): Errors you might encounter when making requests to the Deepgram API
- [API Rate Limits](https://developers.deepgram.com/reference/api-rate-limits.md): Understand the different service limits of Deepgram's APIs.
- [Getting Started](https://developers.deepgram.com/docs/voice-agent.md): Build real-time, interactive voice agents powered by Deepgram's speech-to-text, LLM integration, and text-to-speech, all over a single WebSocket connection.
- [Architecture Overview](https://developers.deepgram.com/docs/voice-agent-architecture.md): One API for the entire voice conversation — listening, thinking, and speaking over a single connection.
- [Build a Voice Agent](https://developers.deepgram.com/docs/build-a-voice-agent.md): Learn how to build a real-time voice agent using Deepgram's Agent API.
- [Build a Voice Agent with Python](https://developers.deepgram.com/docs/build-a-voice-agent-python.md): Create a real-time voice agent using the Deepgram Python SDK.
- [Build a Voice Agent with JavaScript](https://developers.deepgram.com/docs/build-a-voice-agent-javascript.md): Create a real-time voice agent using the Deepgram JavaScript SDK.
- [Build a Voice Agent with C#](https://developers.deepgram.com/docs/build-a-voice-agent-csharp.md): Create a real-time voice agent using the Deepgram .NET SDK.
- [Build a Voice Agent with Go](https://developers.deepgram.com/docs/build-a-voice-agent-go.md): Create a real-time voice agent using the Deepgram Go SDK.
- [Feature Overview](https://developers.deepgram.com/docs/voice-agent-feature-overview.md): Below is a matrix of Deepgram's Voice Agent API features. Please refer to the corresponding documentation for more details.
- [Template Apps](https://developers.deepgram.com/docs/voice-agent-template-apps.md): Get up and running fast with our Voice Agent template applications, fully integrated with Deepgram out-of-the-box.
- [Configure the Voice Agent](https://developers.deepgram.com/docs/configure-voice-agent.md): Learn about the voice agent configuration options for the agent, and both input and output audio.
- [STT Models](https://developers.deepgram.com/docs/voice-agent-stt-models.md): An overview of the speech-to-text models you can use with the Voice Agent API.
- [LLM Models](https://developers.deepgram.com/docs/voice-agent-llm-models.md): An overview of the LLM providers and models you can use with the Voice Agent API.
- [TTS Models](https://developers.deepgram.com/docs/voice-agent-tts-models.md): An overview of Text-to-Speech providers and models you can use with the Voice Agent API.
- [Media Inputs & Outputs](https://developers.deepgram.com/docs/voice-agent-media-inputs-outputs.md): Use different media inputs and outputs when using the Voice Agent API.
- [Prompting Voice Agents](https://developers.deepgram.com/docs/prompting-voice-agents.md): Write effective system prompts that shape how your voice agent behaves on a live call.
- [Multilingual Voice Agents](https://developers.deepgram.com/docs/multilingual-voice-agent.md): Pick the right STT and TTS models for a voice agent that speaks more than one language.
- [Maintaining Context](https://developers.deepgram.com/docs/voice-agent-conversation-context.md): Every lever the Voice Agent API gives you for shaping what the agent knows and remembers across a session.
- [Reusable Agent Configurations](https://developers.deepgram.com/docs/reusable-agent-configurations.md): Learn how to create, store, and reuse agent configurations for the Voice Agent API.
- [Function Calling](https://developers.deepgram.com/docs/voice-agents-function-calling.md): Understand how Voice Agents interact with external APIs and services.
- [Build A Function Call](https://developers.deepgram.com/docs/build-a-function-call.md): Learn how to build a Function Call to use with your Agent.
- [Function Call Request](https://developers.deepgram.com/docs/voice-agent-function-call-request.md): Server-initiated message requesting a function call, to be handled by either client or server
- [Function Call Response](https://developers.deepgram.com/docs/voice-agent-function-call-response.md): Message containing the result of a function call, sent by client or server
- [Function Call Context](https://developers.deepgram.com/docs/voice-agent-function-call-context.md): Provide function call context as part of the conversation history when starting a new Voice Agent session.
- [Browser Agent SDK](https://developers.deepgram.com/docs/browser-agent-overview.md): Four composable packages that connect your web app to Deepgram's Voice Agent API. Works with any JavaScript framework. Ship in minutes, customize for months.
- [JavaScript SDK](https://developers.deepgram.com/docs/browser-agent-javascript.md): API reference for @deepgram/agents — the core WebSocket session, microphone capture, and audio playback with volume and frequency analysis for browser-based voice agents.
- [React Hooks & Provider](https://developers.deepgram.com/docs/browser-agent-react.md): API reference for @deepgram/react — AgentProvider, connection state hooks, playback-aware mode tracking, conversation hooks, component-scoped client tools, and standalone useDeepgramAgent for simpler apps.
- [React UI Components](https://developers.deepgram.com/docs/browser-agent-react-ui.md): API reference for @deepgram/ui — composable components for building voice agent UIs with Deepgram. Includes orb visualizer, waveforms, frequency bars, conversation display, and CSS custom property theming.
- [Widget Embedding Guide](https://developers.deepgram.com/docs/browser-agent-widget.md): How to embed the Deepgram voice agent widget on any web page. Covers CDN and ES module installation, six layout modes, theming with design tokens, callbacks, and programmatic teardown.
- [Build a Multi-Agent Architecture](https://developers.deepgram.com/docs/multi-agent-architecture.md): Create a multi-agent architecture using Deepgram's Voice Agent API, where specialized agents handle different phases of customer interactions through seamless handoffs.
- [Build an Inbound Telephony Agent](https://developers.deepgram.com/docs/inbound-telephony-agent.md): Learn how to build an inbound telephony agent, enabling your customers to dial a phone number and talk to an AI receptionist
- [Build an Inbound Telephony Agent with Plivo](https://developers.deepgram.com/docs/inbound-telephony-agent-plivo.md): Learn how to build an inbound telephony agent with Plivo, enabling your customers to dial a phone number and talk tMeasured from the saved file
Size measures the captured UTF-8 text, not compressed transfer size. Tokens are counted with a named tokenizer; other models can count differently. Neither measure establishes context compatibility or answer quality.
Context architecture
5 H2 sections organize 393 parsed Markdown links. 388 links point to .md or .markdown paths; 0 link occurrences use another hostname. Linked destinations have not been recursively validated.
| H2 section | Links | UTF-8 bytes | Tokens |
|---|---|---|---|
| Instructions for AI AgentsLine 3 | 0 | 265 | 65 |
| DocsLine 9 | 334 | 68378 | 14683 |
| API DocsLine 346 | 55 | 7372 | 1581 |
| OpenAPI SpecificationLine 404 | 2 | 193 | 49 |
| AsyncAPI SpecificationLine 411 | 2 | 212 | 55 |
1 distinct links point to other llms.txt paths. These are routes to more indexes, not proof their contents were included in this file.
Link counts exclude parsed fenced and inline code and resolve relative destinations against the final endpoint. Section sizes cover the text below each H2 until the next H2.
Embedded material
Embedded example text and links to further documentation are counted separately. A code block does not establish that a sample runs or that an authentication flow succeeds.
Publisher prioritization
No H2 section named “Optional” was detected in this file.
The community proposal uses Optional by convention for secondary links that can be skipped for a shorter context. This label does not establish that everything outside it is critical, or that the material inside it is deprecated.
Machine-readable routes
MCP-related text was detected in the captured file. 1 links have MCP-related labels or paths. 0 fenced lines match mcpServers, mcp_servers or an mcp add command.
These are text and link observations. No MCP server connection, authentication or tool call was tested.
Index and bundle
Verified text companion
A verified text response establishes a companion at the checked URL. It does not prove the bundle contains all product documentation, that generation is automated, or that it fits an assistant’s context window.
Change evidence
This capture establishes a baseline. Update frequency cannot be determined from one observation.
2 links have release, changelog, deprecation or migration terms in their labels or paths. These provide places to investigate product changes separately.
File changes can reveal documentation edits or navigation changes. They do not by themselves measure product release velocity, accuracy, agent adoption or AI visibility.
ca160f34fa8a06bcb8134966fe6e972576fbc86acde2d99285805f523f89bd32Counts use a deterministic parser, not a spec-compliance grade. Unusual Markdown and indented code can fall outside its recognized patterns. See the llms.txt proposal and tokenizer implementation.