Artificial intelligence · llms.txt file breakdown
AssemblyAI organizes AssemblyAI content, including Agent Instructions, Core References, Documentation, Website Pages 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.
Complete saved Markdown shown below.
# AssemblyAI
> AssemblyAI provides production-ready Voice AI models for speech-to-text, real-time streaming transcription, speaker diarization, Speech Understanding, Guardrails, the Voice Agent API, and the LLM Gateway. This file indexes the Markdown sources agents should prefer over crawling the HTML marketing site.
## Agent Instructions
- Prefer the Markdown sources linked in this file over crawling HTML pages.
- For documentation pages, append `.md` to the page URL to get the Markdown version (e.g. `https://www.assemblyai.com/docs/voice-agents/voice-agent-api.md`).
- For the complete documentation index, use https://www.assemblyai.com/docs/llms.txt.
- For all documentation in a single file, use https://www.assemblyai.com/docs/llms-full.txt.
- For section-specific documentation indexes, append `/llms.txt` to any docs section URL.
- For coding assistants and agentic IDEs, start with [Build with AI coding agents](https://www.assemblyai.com/docs/agent-instructions.md) and the docs MCP server at https://www.assemblyai.com/docs/mcp.
## Core References
- [Pricing](https://www.assemblyai.com/llms/pricing.md): canonical rate card, billing rules, and add-on stacking.
- [Models & terminology](https://www.assemblyai.com/llms/models.md): model identifiers, language support, deprecations, capability matrices, API parameters, terminology rules, and streaming WebSocket URLs.
## Documentation
- [Documentation index — all pages](https://www.assemblyai.com/docs/llms.txt): the docs team's complete, authoritative index.
- [All documentation in one file](https://www.assemblyai.com/docs/llms-full.txt)
- [Build with AI coding agents](https://www.assemblyai.com/docs/agent-instructions.md): integration guidance for Cursor, Claude Code, Copilot, and other AI coding assistants.
- [Models overview](https://www.assemblyai.com/docs/getting-started/models.md): how to choose a speech model.
- [Universal-3.5 Pro](https://www.assemblyai.com/docs/getting-started/universal-3-pro.md): the flagship speech-to-text model.
- [Transcribe a file — pre-recorded quickstart](https://www.assemblyai.com/docs/pre-recorded-audio/getting-started/transcribe-an-audio-file.md)
- [Transcribe streaming audio — streaming quickstart](https://www.assemblyai.com/docs/streaming/getting-started/transcribe-streaming-audio.md)
- [Voice Agent API](https://www.assemblyai.com/docs/voice-agents/voice-agent-api.md): real-time STT built for voice agents.
- [Speech Understanding](https://www.assemblyai.com/docs/speech-understanding/getting-started.md): LLM-powered analysis over transcripts.
- [LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/overview.md): apply leading LLMs to audio through one API.
- [API reference](https://www.assemblyai.com/docs/api-reference/overview.md)
- [End-to-end examples](https://www.assemblyai.com/docs/getting-started/end-to-end-examples.md)
- [FAQ](https://www.assemblyai.com/docs/faq.md)
## Website Pages
- [Home](https://www.assemblyai.com/index.md)
- [Products overview](https://www.assemblyai.com/products.md)
- [Speech-to-Text](https://www.assemblyai.com/products/speech-to-text.md)
- [Streaming Speech-to-Text](https://www.assemblyai.com/products/streaming-speech-to-text.md)
- [Sync Speech-to-Text](https://www.assemblyai.com/products/sync-speech-to-text.md)
- [Voice Agent API](https://www.assemblyai.com/products/voice-agent-api.md)
- [Speech Understanding](https://www.assemblyai.com/products/speech-understanding.md)
- [Guardrails](https://www.assemblyai.com/products/guardrails.md)
- [LLM Gateway](https://www.assemblyai.com/products/llm-gateway.md)
- [Pricing](https://www.assemblyai.com/pricing.md)
- [Benchmarks](https://www.assemblyai.com/benchmarks.md)
- [Customers](https://www.assemblyai.com/customers.md)
- [Blog](https://www.assemblyai.com/blog.md)
- [Changelog](https://www.assemblyai.com/changelog.md)
## Optional
- [Security](https://www.assemblyai.com/security): security and compliance overview.
Measured 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.
AssemblyAI provides production-ready Voice AI models for speech-to-text, real-time streaming transcription, speaker diarization, Speech Understanding, Guardrails, the Voice Agent API, and the LLM Gateway. This file indexes the Markdown sources agents should prefer over crawling the HTML marketing site.
Context architecture
5 H2 sections organize 31 parsed Markdown links. 28 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 |
|---|---|---|---|
| Agent InstructionsLine 5 | 1 | 707 | 171 |
| Core ReferencesLine 14 | 2 | 322 | 75 |
| DocumentationLine 19 | 13 | 1515 | 383 |
| Website PagesLine 35 | 14 | 921 | 255 |
| OptionalLine 52 · Optional | 1 | 86 | 19 |
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
1 H2 section named “Optional” contain 1 parsed links. 30 links sit outside those sections. That puts 3.2% of the file’s parsed links under Optional.
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. 0 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.
1 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.
65b50f8ca005f5d500c877bec9f03a3bc8d301dfd00ea18f9c49220a833a9061Counts 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.