> ## Documentation Index
> Fetch the complete documentation index at: https://assemblyai.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# AssemblyAI Documentation

> Build with our Voice AI Infrastructure

AssemblyAI provides Voice AI infrastructure: pre-recorded speech-to-text, streaming speech-to-text, synchronous speech-to-text, voice agent orchestration, speech understanding, guardrails and LLM access.

This breaks down into a few core APIs, suited to different parts of your voice product stack.

| Quickstart | Description |
| - | - |
| [Pre-recorded Speech-to-Text API](/docs/pre-recorded-audio/getting-started/transcribe-an-audio-file) | Transcribes recorded audio and video asynchronously across 99 languages, with support on speaker diarization, PII redaction, and more features. Built for teams processing recorded calls, podcasts, or meetings at scale. |
| [Streaming Speech-to-Text API](/docs/streaming/getting-started/transcribe-streaming-audio) | Handles live audio over WebSocket with \~150ms p50 latency, powering voice agents, live captions, and real-time agent-assist tools in contact centers. |
| [Synchronous Speech-to-Text API](/docs/sync-stt/getting-started/transcribe-a-short-audio-file) | Transcribes audio up to 20 minutes long over HTTP (up to 120 seconds through the SDKs or when uploading while recording) in a single request-response call — no polling or webhooks needed. It's suited for quick, low-latency transcription use cases with need for limited transcription features. |
| [Dictation API](/docs/dictation) | Transcribes short audio clips (up to 120 seconds) and formats the text with an LLM in the same request. You include formatting instructions with your audio, and the transcript comes back already cleaned up and formatted. |
| [Voice Agent API](/docs/voice-agents/voice-agent-api) | A fully managed speech-to-speech pipeline — one connection handles STT, LLM reasoning, and TTS together at roughly one second end-to-end latency, for teams that want AssemblyAI to own the whole voice-agent stack rather than assembling it themselves. |
| [Speech Understanding API](/docs/speech-understanding/getting-started) | Layers speech analysis on top of transcripts — summarization, sentiment, topic detection, and more over audio — for extracting structured insight. |
| [Guardrails API](/docs/guardrails/getting-started) | Provides safety, privacy, and compliance controls — PII handling, content moderation, and related safeguards — for teams that need to govern what audio data flows through their pipeline. |
| [LLM Gateway API](/docs/llm-gateway/quickstart) | Gives unified access to frontier language models through the same API, so teams can apply reasoning models to their transcription without a separate integration. |

## Choose how you build

<CardGroup cols={2}>
  <Card title="API reference" icon="code" href="/docs/api-reference">
    Build directly against the raw HTTP and WebSocket API for full control over requests and responses.
  </Card>

  <Card title="SDK" icon="cube" href="/docs/getting-started/sdks">
    Use the Python or TypeScript SDK to integrate transcription, streaming, and voice agents directly into your own codebase.
  </Card>

  <Card title="Build with an AI coding agent" icon="robot" href="/docs/coding-agent-prompts">
    Wire AssemblyAI into Claude Code, Cursor, or any MCP-compatible agent via the AssemblyAI MCP Server and skill.
  </Card>

  <Card title="Integrations" icon="code-fork" iconType="duotone" href="/docs/integrations">
    Drop AssemblyAI into existing voice-agent frameworks and platforms — LiveKit, Pipecat, Twilio, Langflow, and others.
  </Card>
</CardGroup>