# AssemblyAI Documentation

> AssemblyAI provides production-ready Voice AI models for speech-to-text, speaker detection, sentiment analysis, and more. Build with pre-recorded or streaming audio using REST APIs and WebSockets.

This is the structured documentation index for AssemblyAI's public API and product documentation.

## Core machine-readable resources

- [Full documentation content](https://www.assemblyai.com/docs/llms-full.txt): All docs pages and API specs in one file (~4MB). Too large for most agent fetch tools; use the section files below.
- [Integration prompt](https://www.assemblyai.com/docs/agent-instructions.md): Rules of the road for AI coding agents building AssemblyAI integrations.
- [Documentation index](https://www.assemblyai.com/docs/llms.txt): This file.

## Section files

Each file holds the full Markdown of one docs section and is under 100KB, so an agent can read it in one fetch.

- [Overview (part 1 of 3)](https://www.assemblyai.com/docs/llms-full/overview-1.txt): 10 pages; Getting started, Build & Evaluate.
- [Overview (part 2 of 3)](https://www.assemblyai.com/docs/llms-full/overview-2.txt): 11 pages; Build & Evaluate, Administration, Trust & security.
- [Overview (part 3 of 3)](https://www.assemblyai.com/docs/llms-full/overview-3.txt): 1 page; Trust & security.
- [Pre-recorded STT (part 1 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-1.txt): 6 pages; Getting started, Features.
- [Pre-recorded STT (part 2 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-2.txt): 9 pages; Features.
- [Pre-recorded STT (part 3 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-3.txt): 18 pages; Features, API reference, Advanced.
- [Pre-recorded STT (part 4 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-4.txt): 7 pages; Guides.
- [Pre-recorded STT (part 5 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-5.txt): 11 pages; Guides.
- [Pre-recorded STT (part 6 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-6.txt): 9 pages; Guides.
- [Pre-recorded STT (part 7 of 7)](https://www.assemblyai.com/docs/llms-full/pre-recorded-stt-7.txt): 13 pages; Guides.
- [Real-time STT (part 1 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-1.txt): 10 pages; Getting started, Features.
- [Real-time STT (part 2 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-2.txt): 7 pages; Features, API reference, Advanced.
- [Real-time STT (part 3 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-3.txt): 8 pages; Advanced.
- [Real-time STT (part 4 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-4.txt): 1 page; Integrations.
- [Real-time STT (part 5 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-5.txt): 2 pages; Integrations.
- [Real-time STT (part 6 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-6.txt): 3 pages; Integrations, Guides.
- [Real-time STT (part 7 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-7.txt): 2 pages; Guides.
- [Real-time STT (part 8 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-8.txt): 3 pages; Guides.
- [Real-time STT (part 9 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-9.txt): 4 pages; Guides.
- [Real-time STT (part 10 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-10.txt): 5 pages; Guides.
- [Real-time STT (part 11 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-11.txt): 4 pages; Guides.
- [Real-time STT (part 12 of 12)](https://www.assemblyai.com/docs/llms-full/real-time-stt-12.txt): 1 page; Guides.
- [Sync STT (part 1 of 2)](https://www.assemblyai.com/docs/llms-full/sync-stt-1.txt): 14 pages; Getting started, Features, API reference, Advanced.
- [Sync STT (part 2 of 2)](https://www.assemblyai.com/docs/llms-full/sync-stt-2.txt): 2 pages; Integrations.
- [Dictation API](https://www.assemblyai.com/docs/llms-full/dictation-api.txt): 13 pages; Getting started, Features, API reference, Advanced.
- [Text to Speech (part 1 of 4)](https://www.assemblyai.com/docs/llms-full/text-to-speech-1.txt): 6 pages; Getting started, Features.
- [Text to Speech (part 2 of 4)](https://www.assemblyai.com/docs/llms-full/text-to-speech-2.txt): 6 pages; Features, Integrations, API reference.
- [Text to Speech (part 3 of 4)](https://www.assemblyai.com/docs/llms-full/text-to-speech-3.txt): 9 pages; API reference, Advanced.
- [Text to Speech (part 4 of 4)](https://www.assemblyai.com/docs/llms-full/text-to-speech-4.txt): 3 pages; Advanced.
- [Speech Understanding (part 1 of 3)](https://www.assemblyai.com/docs/llms-full/speech-understanding-1.txt): 8 pages; Models & features.
- [Speech Understanding (part 2 of 3)](https://www.assemblyai.com/docs/llms-full/speech-understanding-2.txt): 5 pages; Models & features, Guides.
- [Speech Understanding (part 3 of 3)](https://www.assemblyai.com/docs/llms-full/speech-understanding-3.txt): 1 page; Guides.
- [Guardrails](https://www.assemblyai.com/docs/llms-full/guardrails.txt): 5 pages; Models & features.
- [LLM Gateway (part 1 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-1.txt): 10 pages; Getting started, Gateway features.
- [LLM Gateway (part 2 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-2.txt): 8 pages; Chat completions.
- [LLM Gateway (part 3 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-3.txt): 14 pages; Decisions, API reference, Voice AI Guides.
- [LLM Gateway (part 4 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-4.txt): 4 pages; Voice AI Guides.
- [LLM Gateway (part 5 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-5.txt): 4 pages; Voice AI Guides.
- [LLM Gateway (part 6 of 6)](https://www.assemblyai.com/docs/llms-full/llm-gateway-6.txt): 3 pages; Voice AI Guides.
- [FAQ (part 1 of 2)](https://www.assemblyai.com/docs/llms-full/faq-1.txt): 79 pages; Overview.
- [FAQ (part 2 of 2)](https://www.assemblyai.com/docs/llms-full/faq-2.txt): 15 pages; Overview.
- [Additional pages (part 1 of 2)](https://www.assemblyai.com/docs/llms-full/additional-pages-1.txt): 7 pages.
- [Additional pages (part 2 of 2)](https://www.assemblyai.com/docs/llms-full/additional-pages-2.txt): 4 pages.

## Overview

### Getting started
- [AssemblyAI Documentation](https://www.assemblyai.com/docs/index.md): Build with our Voice AI Infrastructure
- [Build with SDKs](https://www.assemblyai.com/docs/getting-started/sdks.md): Official AssemblyAI SDKs for Python and JavaScript.
- [Build with AI agents](https://www.assemblyai.com/docs/coding-agent-prompts.md): Build with AssemblyAI using Cursor, Claude Code, Copilot, Devin, and other AI coding assistants.
- [Use AssemblyAI in AI apps with the MCP server](https://www.assemblyai.com/docs/mcp-server.md): Connect Claude, Cursor or any MCP client to your AssemblyAI account so it can transcribe, summarize and analyze...
- [Build with integrations](https://www.assemblyai.com/docs/integrations.md): Integrations documentation.
### Build & Evaluate
- [Models](https://www.assemblyai.com/docs/getting-started/models.md): AssemblyAI's speech-to-text and text-to-speech models and their capabilities
- [Evaluations](https://www.assemblyai.com/docs/evaluations.md): Figure out which STT models are best for your product with an evaluation.
### Build & Evaluate > End-to-end examples
- [End-to-end examples](https://www.assemblyai.com/docs/getting-started/end-to-end-examples.md): Copy-paste pipelines that combine multiple AssemblyAI products in a single script.
- [Meeting notetaker](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/meeting-notetaker.md): Transcribe a team meeting with speaker labels, identify speakers by name, then generate structured meeting notes...
- [Sales call intelligence](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/sales-call-intelligence.md): Transcribe a sales call with speaker labels and sentiment analysis, identify speakers by role, then generate a...
- [Medical scribe](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/medical-scribe.md): Transcribe a clinical encounter using Medical Mode with speaker labels and entity detection, then generate a...
- [Content repurposing](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/content-repurposing.md): Transcribe a podcast or webinar, extract key phrases, then generate a blog post draft with LLM Gateway.
- [Real-time meeting assistant](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/real-time-meeting-assistant.md): Stream audio from your microphone with speaker diarization and LLM Gateway for live transcription and automatic...
- [Real-time live captioner](https://www.assemblyai.com/docs/getting-started/end-to-end-examples/real-time-live-captioner.md): Stream audio from your microphone with keyterms prompting for domain-specific accuracy, ideal for live events and...
### Administration
- [Account Management](https://www.assemblyai.com/docs/account-management.md)
- [Temporary tokens](https://www.assemblyai.com/docs/temporary-tokens.md): Mint a short-lived token on your server so a browser or app can use an AssemblyAI product without your API key, and...
- [Single Sign-On (SSO)](https://www.assemblyai.com/docs/sso.md): Set up SAML or OIDC Single Sign-On for your AssemblyAI organization, including step-by-step configuration for Okta,...
- [Billing and Pricing](https://www.assemblyai.com/docs/billing-and-pricing.md)
### Trust & security
- [Trust center](https://assembly.ai/trust)
- [Security overview](https://www.assemblyai.com/security)
- [Data Controls](https://www.assemblyai.com/docs/data-controls.md): Manage how AssemblyAI retains and uses your data — opt out of the model improvement program, set a time-to-live for...
- [Data retention and model training](https://www.assemblyai.com/docs/data-retention-and-model-training.md): Learn about how AssemblyAI handles data retention, encryption, model training, and compliance.

## Pre-recorded STT

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/pre-recorded-audio/getting-started/transcribe-an-audio-file.md): Learn how to transcribe and analyze an audio file.
- [Model selection](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-speech-model.md)
### Features
- [Prompting and Keyterms](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro/prompting.md)
- [Medical Mode](https://www.assemblyai.com/docs/pre-recorded-audio/medical-mode.md): Improve transcription accuracy for medical terminology in pre-recorded audio
- [Speaker Diarization](https://www.assemblyai.com/docs/pre-recorded-audio/label-speakers.md): Add speaker labels to your transcript
- [Multichannel Transcription](https://www.assemblyai.com/docs/pre-recorded-audio/transcribe-multiple-audio-channels.md)
- [Code Switching](https://www.assemblyai.com/docs/pre-recorded-audio/code-switching.md)
### Features > Languages
- [Automatic Language Detection](https://www.assemblyai.com/docs/pre-recorded-audio/language-detection.md): Detect the dominant language and automatically route your request to the best available speech model for that language.
- [Set Language Manually](https://www.assemblyai.com/docs/pre-recorded-audio/set-language-manually.md): Specify a dominant language via language_code to route your request to the best available speech model for that...
- [Supported Languages](https://www.assemblyai.com/docs/pre-recorded-audio/supported-languages.md): Supported languages for pre-recorded audio speech-to-text models.
### Features
- [Custom Spelling](https://www.assemblyai.com/docs/pre-recorded-audio/correct-spelling-of-terms.md)
- [Formatting](https://www.assemblyai.com/docs/pre-recorded-audio/formatting.md): Control text formatting and normalization in pre-recorded audio transcripts.
- [Filler Words](https://www.assemblyai.com/docs/pre-recorded-audio/include-filler-words.md)
- [Word Search](https://www.assemblyai.com/docs/pre-recorded-audio/search-for-words-in-transcript.md)
- [Set the Start and End of the Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/set-the-start-and-end-of-the-transcript.md)
### Features > Transcription operations
- [Transcript Status](https://www.assemblyai.com/docs/pre-recorded-audio/check-transcript-status.md)
- [Transcript export options](https://www.assemblyai.com/docs/pre-recorded-audio/export-transcripts-as-srt-vtt-or-text.md)
- [Delete Transcripts](https://www.assemblyai.com/docs/pre-recorded-audio/delete-transcripts.md)
### API reference
- [Upload a media file](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/files/upload.md): Upload a media file to AssemblyAI.
- [Transcribe audio](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/submit.md): Create a transcription request.
- [Get a transcript](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get.md): Retrieve a transcript by ID.
- [Get transcript sentences](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-sentences.md): Retrieve transcript sentences.
- [Get transcript paragraphs](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-paragraphs.md): Retrieve transcript paragraphs.
- [Get subtitles](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-subtitles.md): Export subtitles for a transcript.
- [Get redacted audio](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/get-redacted-audio.md): Retrieve redacted audio for a transcript.
- [Word search](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/word-search.md): Search a transcript for words or phrases.
- [List transcripts](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/list.md): List transcripts.
- [Delete a transcript](https://www.assemblyai.com/docs/pre-recorded-audio/api-reference/transcripts/delete.md): Delete a transcript.
### Advanced
- [Webhooks for pre-recorded audio](https://www.assemblyai.com/docs/pre-recorded-audio/webhooks.md): Get notified when a pre-recorded audio transcription is ready.
- [Benchmarks](https://www.assemblyai.com/docs/pre-recorded-audio/benchmarks.md): Industry-leading accuracy for pre-recorded speech-to-text.
- [Evaluating Pre-recorded STT models](https://www.assemblyai.com/docs/pre-recorded-audio/evaluations.md)
- [Cloud Endpoints and Data Residency](https://www.assemblyai.com/docs/pre-recorded-audio/select-the-region.md)
- [Rate limits](https://www.assemblyai.com/docs/pre-recorded-audio/rate-limits.md)
### Guides > Migration guides
- [Migration guide: Deepgram to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/dg_to_aai.md)
- [Migration guide: OpenAI to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/oai_to_aai.md)
- [Migration guide: AWS Transcribe to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/aws_to_aai.md)
- [Migration guide: Google Speech-to-Text to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/google_to_aai.md)
- [Migration guide: Gladia to AssemblyAI](https://www.assemblyai.com/docs/pre-recorded-audio/migration-guides/gladia_to_aai.md)
### Guides > Tutorials
- [Best Practices for building Meeting Notetakers](https://www.assemblyai.com/docs/meeting-notetaker-best-practices.md): Complete guide for building meeting notetakers with AssemblyAI
- [Build a medical scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices.md): Build AI-powered medical scribes that transcribe patient encounters and generate clinical documentation.
- [Best Practices for building Contact Center Applications](https://www.assemblyai.com/docs/contact-center-best-practices.md): Complete guide for building contact center applications with AssemblyAI
### Guides > Tutorials > Basic transcription workflows
- [Get YouTube Video Transcripts with yt-dlp](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribe_youtube_videos.md)
- [Build a UI for Transcription with Gradio and Python](https://www.assemblyai.com/docs/pre-recorded-audio/guides/gradio-frontend.md)
- [Detect Low Confidence Words in a Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/detecting-low-confidence-words.md)
### Guides > Tutorials > Batch transcription
- [Running Bulk Transcription and Load Tests at Scale](https://www.assemblyai.com/docs/pre-recorded-audio/guides/bulk-transcription-and-load-tests-at-scale.md): Best practices for submitting large volumes of audio files for transcription, including one-off load tests.
- [Transcribe Multiple Files Simultaneously Using the JavaScript SDK](https://www.assemblyai.com/docs/pre-recorded-audio/guides/sdk-node-batch.md)
- [Transcribe Multiple Files Simultaneously Using the Python SDK](https://www.assemblyai.com/docs/pre-recorded-audio/guides/batch_transcription.md)
### Guides > Tutorials > Hosting audio files
- [Transcribe from an S3 Bucket](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribe_from_s3.md)
- [Transcribe Google Drive Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribing-google-drive-file.md)
- [Transcribe GitHub Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/transcribing-github-files.md)
### Guides > Tutorials > Speaker labels
- [Iterate over Speaker Labels with Make.com](https://www.assemblyai.com/docs/pre-recorded-audio/guides/make-speaker-labels.md)
- [Calculate the Talk / Listen Ratio of Speakers](https://www.assemblyai.com/docs/pre-recorded-audio/guides/talk-listen-ratio.md)
- [Plot A Speaker Timeline with Matplotlib](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker_timeline.md)
- [Generate Custom Speaker Labels with Pyannote](https://www.assemblyai.com/docs/pre-recorded-audio/guides/Use_AssemblyAI_with_Pyannote_to_generate_custom_Speaker_Labels.md)
- [Use Speaker Diarization with Async Chunking](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker-diarization-with-async-chunking.md)
- [Setup A Speaker Identification System using Pinecone & Nvidia TitaNet](https://www.assemblyai.com/docs/pre-recorded-audio/guides/titanet-speaker-identification.md)
### Guides > Tutorials > Automatic Language Detection
- [Use Automatic Language Detection as a Separate Step From Transcription](https://www.assemblyai.com/docs/pre-recorded-audio/guides/automatic-language-detection-separate.md)
- [Route to Default Language if Language Confidence is Low](https://www.assemblyai.com/docs/pre-recorded-audio/guides/automatic-language-detection-route-default-language.md)
### Guides > Tutorials > Subtitles
- [Create Custom Length Subtitles](https://www.assemblyai.com/docs/pre-recorded-audio/guides/subtitle_creation_by_word_count.md)
- [Create Subtitles with Speaker Labels](https://www.assemblyai.com/docs/pre-recorded-audio/guides/speaker_labelled_subtitles.md)
- [Generate Subtitles for Videos](https://www.assemblyai.com/docs/pre-recorded-audio/guides/subtitles.md)
- [Translate an AssemblyAI Subtitle Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_subtitles.md)
### Guides > Tutorials > Delete transcripts
- [Schedule a DELETE request with AssemblyAI and EasyCron](https://www.assemblyai.com/docs/pre-recorded-audio/guides/schedule_delete.md)
### Guides > Tutorials > Error handling and audio file fixes
- [Troubleshoot Common Errors](https://www.assemblyai.com/docs/pre-recorded-audio/guides/common_errors_and_solutions.md)
- [Implement Retry Server Error Logic](https://www.assemblyai.com/docs/pre-recorded-audio/guides/retry-server-error.md)
- [Implement Retry Upload Error Logic](https://www.assemblyai.com/docs/pre-recorded-audio/guides/retry-upload-error.md)
- [Identify Duplicate Dual Channel Files](https://www.assemblyai.com/docs/pre-recorded-audio/guides/identify_duplicate_channels.md)
- [Correct Audio Duration Discrepancies with Multi-Tool Validation and Transcoding](https://www.assemblyai.com/docs/pre-recorded-audio/guides/audio-duration-fix.md)
- [Audio File Downsampling Recommendations and Best Practices](https://www.assemblyai.com/docs/pre-recorded-audio/guides/downsampling.md): Learn best practices for reducing audio file size while maintaining transcription quality with AssemblyAI
### Guides > Tutorials > Translation
- [Translate an AssemblyAI Subtitle Transcript](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_subtitles.md)
- [Translate AssemblyAI Transcripts Into Other Languages Using Commercial Models](https://www.assemblyai.com/docs/pre-recorded-audio/guides/translate_transcripts.md)
- [Transform Chinese transcripts into Simplified or Traditional Text](https://www.assemblyai.com/docs/pre-recorded-audio/guides/traditional_simplified_chinese.md)
### Guides > Tutorials > Do more with our SDKs
- [Do More With Our SDKs](https://www.assemblyai.com/docs/pre-recorded-audio/guides/do-more-with-sdk.md)

## Real-time STT

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/streaming/getting-started/transcribe-streaming-audio.md): Learn how to transcribe streaming audio.
- [Model selection](https://www.assemblyai.com/docs/streaming/select-the-speech-model.md)
- [Optimizing Accuracy and Latency](https://www.assemblyai.com/docs/streaming/getting-started/optimizing-accuracy-and-latency.md): Tune streaming models to balance transcription accuracy and latency.
### Features
- [Turn Detection](https://www.assemblyai.com/docs/streaming/turn-detection.md)
- [Prompting and Keyterms](https://www.assemblyai.com/docs/streaming/prompting-and-keyterms.md)
- [Conversation Context](https://www.assemblyai.com/docs/streaming/universal-3-5-pro/context-carryover.md)
- [Multilingual Transcription](https://www.assemblyai.com/docs/streaming/multilingual-transcription.md)
- [Real-time Translation](https://www.assemblyai.com/docs/streaming/real-time-translation.md): Translate each streaming transcript turn into another language on the same WebSocket connection using the...
- [Medical Mode](https://www.assemblyai.com/docs/streaming/medical-mode.md)
- [Voice Focus](https://www.assemblyai.com/docs/streaming/voice-focus.md)
- [Streaming Diarization and Multichannel](https://www.assemblyai.com/docs/streaming/label-speakers-and-separate-channels.md)
- [PII Redaction](https://www.assemblyai.com/docs/streaming/pii-redaction.md)
- [Filter profanity](https://www.assemblyai.com/docs/streaming/filter-profanity-from-transcripts.md)
### API reference
- [Message Sequence](https://www.assemblyai.com/docs/streaming/message-sequence.md): Canonical reference for the streaming WebSocket protocol.
- [Streaming WebSocket API](https://www.assemblyai.com/docs/streaming/api-spec/streaming-websocket.md): Full AsyncAPI reference for the Real-time STT WebSocket API.
- [Generate streaming token](https://www.assemblyai.com/docs/streaming/api-spec/generate-streaming-token.md): Generate a temporary token for Real-time STT.
### Advanced
- [Authenticate with a temporary token](https://www.assemblyai.com/docs/streaming/authenticate-with-a-temporary-token.md)
- [Webhooks for streaming speech-to-text](https://www.assemblyai.com/docs/streaming/webhooks.md): Get notified when a streaming transcription session ends.
- [Updating Configuration Mid-Stream](https://www.assemblyai.com/docs/streaming/updating-configuration-mid-stream.md): Update streaming session parameters without reconnecting using the UpdateConfiguration message.
- [Common session errors and closures](https://www.assemblyai.com/docs/streaming/common-session-errors-and-closures.md)
- [Benchmarks](https://www.assemblyai.com/docs/streaming/benchmarks.md): Industry-leading accuracy for streaming speech-to-text.
- [Evaluating Real-time STT models for Voice Agents](https://www.assemblyai.com/docs/streaming/evaluations/voice-agents.md)
- [Streaming Endpoints and Data Zones](https://www.assemblyai.com/docs/streaming/endpoints-and-data-zones.md)
- [Rate limits](https://www.assemblyai.com/docs/streaming/rate-limits.md)
- [Self-Hosted Streaming](https://www.assemblyai.com/docs/streaming/self-hosted-streaming.md): Deploy AssemblyAI's streaming transcription solution within your own infrastructure
### Integrations
- [Universal-3.6 Pro on LiveKit](https://www.assemblyai.com/docs/voice-agents/livekit-universal-3-6-pro.md): Integrate AssemblyAI's Universal-3.6 Pro speech-to-text model into a LiveKit voice agent
- [Universal-3.6 Pro on Pipecat](https://www.assemblyai.com/docs/voice-agents/pipecat-universal-3-5-pro.md): Integrate AssemblyAI's Universal-3.6 Pro speech-to-text model into a Pipecat voice agent
- [Universal-3.6 Pro on Vapi](https://www.assemblyai.com/docs/voice-agents/vapi.md): Configure AssemblyAI's Universal-3.6 Pro speech-to-text model as the transcriber for a Vapi voice assistant
- [Universal-3.6 Pro on Bolna](https://www.assemblyai.com/docs/voice-agents/bolna.md): Use AssemblyAI's Universal-3.6 Pro speech-to-text model as the transcriber in a Bolna voice agent
### Guides > Migration guides
- [Streaming Migration Guide: Universal Streaming to Universal-3.6 Pro Realtime](https://www.assemblyai.com/docs/streaming/migration-guides/universal-to-universal-3-5-pro-streaming.md)
- [Streaming Migration Guide: Deepgram to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/dg_to_aai_streaming.md)
- [Migration guide: Speechmatics to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/speechmatics_to_aai_streaming.md)
- [Streaming Migration Guide: Gladia to AssemblyAI](https://www.assemblyai.com/docs/streaming/migration-guides/gladia-to-aai-streaming.md)
### Guides > Tutorials
- [Best Practices for building Meeting Notetakers](https://www.assemblyai.com/docs/meeting-notetaker-best-practices.md): Complete guide for building meeting notetakers with AssemblyAI
- [Build a medical scribe](https://www.assemblyai.com/docs/medical-scribe-best-practices.md): Build AI-powered medical scribes that transcribe patient encounters and generate clinical documentation.
- [Best Practices for Building Voice Agents](https://www.assemblyai.com/docs/voice-agents/best-practices.md): Complete guide for building voice agents with AssemblyAI's Universal-3 Pro Streaming
- [Best Practices for building Contact Center Applications](https://www.assemblyai.com/docs/contact-center-best-practices.md): Complete guide for building contact center applications with AssemblyAI
### Guides > Tutorials > Basic streaming workflows
- [Stream a pre-recorded file in real time](https://www.assemblyai.com/docs/streaming/guides/stream_prerecorded_file_realtime.md)
- [Transcribe System Audio in Real-Time (macOS)](https://www.assemblyai.com/docs/streaming/guides/transcribe_system_audio.md)
- [Terminate Streaming Session After Inactivity](https://www.assemblyai.com/docs/streaming/guides/terminate_realtime_programmatically.md)
- [Migrating from Streaming v2 to Streaming v3 (Python)](https://www.assemblyai.com/docs/streaming/guides/v2_to_v3_migration.md)
- [Migrating from Streaming v2 to Streaming v3 (JavaScript)](https://www.assemblyai.com/docs/streaming/guides/v2_to_v3_migration_js.md)
### Guides > Tutorials > Streaming for front-end applications
- [Next.js example using Real-time STT](https://github.com/AssemblyAI-Community/streaming-api-nextjs)
- [Vanilla Javascript example using Real-time STT](https://github.com/AssemblyAI/realtime-transcription-browser-js-example)
### Guides > Tutorials > Streaming with LLM Gateway
- [Apply LLM Gateway to Streaming](https://www.assemblyai.com/docs/streaming/guides/real_time_llm_gateway.md): Learn how to analyze streaming audio transcripts using LLM Gateway.
- [Translate Real-time STT Transcripts with LLM Gateway](https://www.assemblyai.com/docs/streaming/guides/real_time_translation.md)
### Guides > Tutorials > Use-case specific streaming workflows
- [Apply Noise Reduction to Audio for Streaming Speech-to-Text](https://www.assemblyai.com/docs/streaming/guides/noise_reduction_streaming.md)
- [Transcribe audio files with Streaming](https://www.assemblyai.com/docs/streaming/guides/streaming_transcribe_audio_file.md)
- [Evaluate Streaming transcription accuracy with WER](https://www.assemblyai.com/docs/streaming/guides/evaluate_streaming_wer.md)
- [Determine Optimal Turn Detection Settings from Historical Audio Analysis](https://www.assemblyai.com/docs/streaming/guides/turn_detection_improvement_using_async.md)

## Sync STT

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/sync-stt/getting-started/quickstart.md): Go from a microphone to a finished transcript in one HTTP call, with the upload happening while the person is still...
- [Transcribe a short audio file](https://www.assemblyai.com/docs/sync-stt/getting-started/transcribe-a-short-audio-file.md): Learn how to transcribe an audio file synchronously with the Sync API.
- [Transcribe live audio](https://www.assemblyai.com/docs/sync-stt/getting-started/transcribe-live-audio.md): Upload audio to the Sync API as it is recorded, so the transcript is ready almost as soon as the speaker stops.
### Features
- [Prompting and Keyterms](https://www.assemblyai.com/docs/sync-stt/prompting-and-keyterms.md)
- [Conversation context](https://www.assemblyai.com/docs/sync-stt/conversation-context.md): Improve multi-turn transcription accuracy by passing prior dialogue with each request.
- [Language selection](https://www.assemblyai.com/docs/sync-stt/language-selection.md): Steer Sync STT transcription toward one or more languages with the language_codes field.
- [Word timestamps](https://www.assemblyai.com/docs/sync-stt/word-timestamps.md): Get exact per-word start and end times with your synchronous transcript.
### API reference
- [Transcribe a short audio file](https://www.assemblyai.com/docs/api-reference/sync-api/transcribe.md): Synchronously transcribe an audio file up to 20 minutes long.
- [Transcribe live audio](https://www.assemblyai.com/docs/api-reference/sync-api/transcribe-live.md): Upload audio to the Sync API as it is recorded and receive the transcript when the audio ends.
- [Pre-warm a connection](https://www.assemblyai.com/docs/api-reference/sync-api/warm.md): Establish the HTTPS connection ahead of a /v1/transcribe request to take the TLS handshake off the critical path.
### Advanced
- [Audio requirements](https://www.assemblyai.com/docs/sync-stt/audio-requirements.md): Duration, size, format, and sample-rate constraints for Sync STT audio.
- [Error handling](https://www.assemblyai.com/docs/sync-stt/error-handling.md): Sync STT error responses, status codes, and retry guidance.
- [Cloud endpoints & data residency](https://www.assemblyai.com/docs/sync-stt/endpoints-and-data-zones.md): AssemblyAI Sync STT endpoints for global routing and US/EU data residency.
- [Connection pre-warming](https://www.assemblyai.com/docs/sync-stt/connection-pre-warming.md): Use the /v1/warm endpoint to take the TLS handshake off the critical path of a synchronous transcription request.
### Integrations
- [Sync STT on Pipecat](https://www.assemblyai.com/docs/sync-stt/pipecat.md): Build a Pipecat voice agent that transcribes each turn with a single Sync STT request instead of a streaming WebSocket
- [Sync STT on OpenRouter](https://www.assemblyai.com/docs/sync-stt/openrouter.md): Transcribe with Universal-3.5 Pro through OpenRouter's OpenAI-compatible transcription API

## Dictation API

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/dictation.md): Turn a spoken utterance into a clean dictation in under a second, with the verbatim transcript alongside it.
- [Achieve lowest latency](https://www.assemblyai.com/docs/dictation/uploading-while-recording.md): Start the request before the speaker stops, so most of the utterance is uploaded by the time they finish.
- [Recordings over two minutes](https://www.assemblyai.com/docs/dictation/recordings-over-two-minutes.md): Start every dictation on the live endpoint, and fall back to the finished-recording endpoint when the user talks for...
- [Examples](https://www.assemblyai.com/docs/dictation/examples.md): End-to-end Dictation requests for a clinical note and a travel booking, showing how the config fields work together.
### Features
- [Transcript rewriting](https://www.assemblyai.com/docs/dictation/transcript-rewriting.md): Reshape a dictated transcript with llm_instruction, alongside the verbatim one.
- [Prompting and keyterms](https://www.assemblyai.com/docs/dictation/prompting-and-keyterms.md): Contextual prompting and keyterms biasing for dictated transcription.
- [Language selection](https://www.assemblyai.com/docs/dictation/language-selection.md): Steer Dictation transcription toward one or more languages with the language_codes field.
### API reference
- [Transcribe while recording](https://www.assemblyai.com/docs/api-reference/dictation-api/transcribe-live.md): Send a spoken utterance to the Dictation API and receive send-ready cleaned-up text alongside the verbatim transcript.
- [Transcribe a finished recording](https://www.assemblyai.com/docs/api-reference/dictation-api/transcribe.md): Send a finished recording of up to 20 minutes, including compressed formats, to the Dictation API and receive...
### Advanced
- [Audio requirements](https://www.assemblyai.com/docs/dictation/audio-requirements.md): Duration, format, and sample-rate constraints for Dictation audio.
- [Error handling](https://www.assemblyai.com/docs/dictation/error-handling.md): Dictation API error responses, status codes, and retry guidance.
- [Cloud endpoints & data residency](https://www.assemblyai.com/docs/dictation/endpoints-and-data-zones.md): AssemblyAI Dictation endpoints for global routing and US/EU data residency.
- [Reduce connection overhead](https://www.assemblyai.com/docs/dictation/connection-pre-warming.md): Use the /warm endpoint to take the TLS handshake off the critical path of a dictation request.

## Text to Speech

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/tts/getting-started/quickstart.md): Turn a line of text into a WAV file with one SDK call or one HTTP request, then speak a whole reply over a single...
- [Optimizing Accuracy and Latency](https://www.assemblyai.com/docs/tts/getting-started/optimizing-accuracy-and-latency.md): Get the first audio of each reply sooner, and have the text read the way you mean it.
- [Choose an interface](https://www.assemblyai.com/docs/tts/getting-started/choose-an-interface.md): The SDKs, the HTTP API, the WebSocket API, the OpenAI-compatible route and the LiveKit and Pipecat plugins, and...
### Features
- [Voices](https://www.assemblyai.com/docs/tts/voices.md): Name a voice with voice_id in the SDKs and on the wire, where to find voices, the ones to start with, and how voice...
- [Voice cloning](https://www.assemblyai.com/docs/tts/cloned-voices.md): What a cloned voice is, how to create one in the AssemblyAI dashboard, how to speak with it or with a library voice...
- [Prompting guide](https://www.assemblyai.com/docs/tts/prompting-guide.md): How the text you send shapes the speech, from pacing and tone to how numbers, dates and other entities are read, and...
- [Word boundaries](https://www.assemblyai.com/docs/tts/word-boundaries.md): Per-word timings for synthesized speech, for highlighting text in sync with playback.
### Integrations
- [Streaming TTS on LiveKit](https://www.assemblyai.com/docs/tts/livekit.md): Give a LiveKit voice agent an AssemblyAI voice with the assemblyai.TTS plugin, with word-aligned transcripts and...
- [Streaming TTS on Pipecat](https://www.assemblyai.com/docs/tts/pipecat.md): Give a Pipecat voice agent an AssemblyAI voice with AssemblyAITTSService, with word-timed context and barge-in on...
- [Streaming TTS on OpenRouter](https://www.assemblyai.com/docs/tts/openrouter.md): Synthesize speech with AssemblyAI voices through OpenRouter's OpenAI-compatible speech API, on your OpenRouter key...
- [OpenAI compatibility](https://www.assemblyai.com/docs/tts/openai-compatibility.md): Point an OpenAI SDK, or a framework built on one, at Streaming TTS and keep the code you have.
### API reference > WebSocket API
- [WebSocket API basics](https://www.assemblyai.com/docs/tts/connect-parameters.md): Hosts, authentication, the connect sequence, the parameter rules, the Begin echo and the idle timeout that every...
- [Message frames](https://www.assemblyai.com/docs/tts/message-frames.md): Every frame in the Streaming TTS protocol, in both directions, with the order they arrive in.
- [Streaming TTS WebSocket API](https://www.assemblyai.com/docs/tts/api-reference/websocket-api.md): Full AsyncAPI reference for the Streaming TTS WebSocket API.
### API reference > HTTP API
- [HTTP API basics](https://www.assemblyai.com/docs/tts/api-reference/http-api/overview.md): Hosts, authentication, response framing, errors, limits, latency and billing of the Streaming TTS HTTP API.
- [Create speech](https://www.assemblyai.com/docs/tts/api-reference/http-api/create-speech.md): Turn a text into speech in one request, streamed as it is synthesized or returned as a whole file.
- [Stream speech with word timings](https://www.assemblyai.com/docs/tts/api-reference/http-api/stream-speech-events.md): Stream synthesized speech as server-sent events, with the time at which each word is spoken.
- [Create speech (OpenAI compatible)](https://www.assemblyai.com/docs/tts/api-reference/http-api/create-speech-openai.md): The OpenAI speech request shape, so OpenAI SDKs and the frameworks built on them work with a new base URL.
- [List models (OpenAI compatible)](https://www.assemblyai.com/docs/tts/api-reference/http-api/list-openai-models.md): The model names of the OpenAI-compatible speech route, as an OpenAI model list.
- [List models (OpenRouter)](https://www.assemblyai.com/docs/tts/api-reference/http-api/list-openrouter-models.md): The models of the OpenAI-compatible speech route in OpenRouter's provider document format.
### Advanced
- [Authenticate with a temporary token](https://www.assemblyai.com/docs/tts/authenticate-with-a-temporary-token.md): Mint a short-lived token on your server so a browser or an app can open a Streaming TTS session without your API key.
- [Error handling](https://www.assemblyai.com/docs/tts/error-handling.md): Streaming TTS Error frames, WebSocket close codes, HTTP API errors, and how to tell a real failure from a finished...
- [Limits](https://www.assemblyai.com/docs/tts/limits.md): Text, session, and rate limits on a Streaming TTS session or HTTP request, and how each one reports a breach.
- [Cloud endpoints & data residency](https://www.assemblyai.com/docs/tts/endpoints-and-data-zones.md): The US and EU Streaming TTS endpoints for the WebSocket and HTTP APIs, where each processes your data, and how to...

## Speech Understanding

### Models & features
- [Speech Understanding](https://www.assemblyai.com/docs/speech-understanding/getting-started.md): Extract structured insights from audio with Speech Understanding models.
- [Action Items](https://www.assemblyai.com/docs/speech-understanding/action-items.md): Generate action items of your audio transcripts
- [Rate limits](https://www.assemblyai.com/docs/speech-understanding/rate-limits.md)
- [Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/auto-chapters.md): Automatically segment your audio into chapters with summaries using LLM Gateway
- [Custom Formatting](https://www.assemblyai.com/docs/speech-understanding/custom-formatting.md): Automatically format dates, phone numbers, emails, and more in your transcripts
- [Entity Detection](https://www.assemblyai.com/docs/speech-understanding/entity-detection.md): Extract named entities from your audio file
- [Key Phrases](https://www.assemblyai.com/docs/speech-understanding/key-phrases.md): Label key phrases that are spoken in your audio
- [Sentiment Analysis](https://www.assemblyai.com/docs/speech-understanding/sentiment-analysis.md): Detect the sentiment of speech in your audio
- [Speaker Identification](https://www.assemblyai.com/docs/speech-understanding/speaker-identification.md): Identify speakers by name or role in your transcript
- [Summarization](https://www.assemblyai.com/docs/speech-understanding/summarization.md): Generate summaries of your audio transcripts
- [Topic Detection](https://www.assemblyai.com/docs/speech-understanding/topic-detection.md): Label topics that are mentioned in your audio file
- [Translation](https://www.assemblyai.com/docs/speech-understanding/translation.md): Translate your transcripts from one language to another
### Guides > Migration guides
- [Migration guide: Auto Chapters](https://www.assemblyai.com/docs/speech-understanding/migration-guides/auto-chapters.md)
- [Migration guide: Summarization](https://www.assemblyai.com/docs/speech-understanding/migration-guides/summarization.md)

## Guardrails

### Models & features
- [Guardrails](https://www.assemblyai.com/docs/guardrails/getting-started.md): Protect sensitive content in your transcripts with guardrail features.
- [PII Redaction](https://www.assemblyai.com/docs/guardrails/redact-pii-from-transcripts.md): Redact PII that is spoken in your audio
- [Content Moderation](https://www.assemblyai.com/docs/guardrails/detect-sensitive-content.md): Detect sensitive content in your audio files
- [Profanity Filtering](https://www.assemblyai.com/docs/guardrails/filter-profanity-from-transcripts.md)
- [Speech Threshold](https://www.assemblyai.com/docs/guardrails/set-minimum-speech-threshold.md)

## LLM Gateway

### Getting started
- [Quickstart](https://www.assemblyai.com/docs/llm-gateway/quickstart.md): AssemblyAI's LLM Gateway is a unified API providing access to 25+ models from Claude, GPT, Gemini, and more through...
- [Model Catalog](https://www.assemblyai.com/products/llm-gateway/models): Open the LLM Gateway model catalog.
- [Choose a model](https://www.assemblyai.com/docs/llm-gateway/choose-a-model.md): Pick the best LLM Gateway model for voice post-processing tasks like summarization, extraction, text correction, and...
- [Providers](https://www.assemblyai.com/docs/llm-gateway/providers.md): Model providers available through LLM Gateway, including data retention policies and regional availability
### Gateway features
- [Model Fallbacks](https://www.assemblyai.com/docs/llm-gateway/fallback.md): Automatically fall back to an alternative LLM model when your primary model fails
- [Prompt Caching](https://www.assemblyai.com/docs/llm-gateway/prompt-caching.md): Reduce latency and costs by caching repeated prompt content across LLM Gateway requests
- [Cloud Endpoints and Data Residency](https://www.assemblyai.com/docs/llm-gateway/cloud-endpoints-and-data-residency.md): Choose LLM Gateway endpoints for data residency requirements.
- [Manage rate limits](https://www.assemblyai.com/docs/llm-gateway/rate-limits.md): Understand LLM Gateway request and token rate limits, why you get a 429, how max_tokens affects your allowance, and...
- [Improve Latency](https://www.assemblyai.com/docs/llm-gateway/improve-latency.md): Use keep-alive connections to minimize latency
- [Troubleshooting](https://www.assemblyai.com/docs/llm-gateway/troubleshooting.md): Common issues and fixes when using the LLM Gateway.
### Chat completions
- [Basic Chat Completions](https://www.assemblyai.com/docs/llm-gateway/chat-completions.md): Send simple messages and receive responses from LLM models
- [Multi-turn Conversations](https://www.assemblyai.com/docs/llm-gateway/conversations.md): Maintain context across multiple exchanges with conversation history
- [Tool Calling](https://www.assemblyai.com/docs/llm-gateway/tool-calling.md): Enable models to execute custom functions to access external data or functionality
- [Structured Outputs](https://www.assemblyai.com/docs/llm-gateway/structured-outputs.md): Constrain model responses to follow a specific JSON schema for reliable, parseable outputs
- [Agentic Workflows](https://www.assemblyai.com/docs/llm-gateway/agentic-workflows.md): Build multi-step reasoning applications with automatic tool chaining
- [Saved prompts and prompt templates](https://www.assemblyai.com/docs/llm-gateway/saved-prompts.md): Store a prompt in LLM Gateway under a name, then run it by name with values filled in per request
- [Prompt Engineering for LLM Gateway](https://www.assemblyai.com/docs/llm-gateway/prompt-engineering.md): Learn how to improve your prompts for LLM Gateway.
- [Ask Questions About Your Audio Transcripts](https://www.assemblyai.com/docs/llm-gateway/ask-questions.md): Ask questions about your audio transcripts using LLM Gateway.
### Decisions
- [Decisions](https://www.assemblyai.com/docs/llm-gateway/decisions.md): Get typed, calibrated answers to a list of questions about an input with LLM Gateway's decisions endpoint
### API reference
- [Create a chat completion](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-chat-completion.md): Create a chat completion with LLM Gateway.
- [Create speech understanding](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-speech-understanding.md): Apply LLM Gateway to audio transcripts.
- [List available models](https://www.assemblyai.com/docs/llm-gateway/api-reference/list-available-models.md): List the models available through LLM Gateway.
- [Create a saved prompt](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-saved-prompt.md): Create a saved prompt for use with LLM Gateway.
- [Get a saved prompt](https://www.assemblyai.com/docs/llm-gateway/api-reference/get-saved-prompt.md): Get a saved prompt from LLM Gateway.
- [Update a saved prompt](https://www.assemblyai.com/docs/llm-gateway/api-reference/update-saved-prompt.md): Update a saved prompt in LLM Gateway.
- [Delete a saved prompt](https://www.assemblyai.com/docs/llm-gateway/api-reference/delete-saved-prompt.md): Delete a saved prompt from LLM Gateway.
- [Create a decision](https://www.assemblyai.com/docs/llm-gateway/api-reference/create-decision.md): Answer typed questions about an input with LLM Gateway.
### Voice AI Guides
- [Apply LLM Gateway to Audio Transcripts](https://www.assemblyai.com/docs/llm-gateway/apply-llms-to-audio-files.md): Learn how to analyze audio transcripts using LLM Gateway.
### Voice AI Guides > Basic LLM Gateway workflows
- [Setup An AI Coach With LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-ai-coach.md)
- [Generate Action Items with LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-action-items.md)
- [Prompt A Structured Q&A Response Using LLM Gateway](https://www.assemblyai.com/docs/guides/task-endpoint-structured-QA.md)
- [Estimate Input Token Costs for LLM Gateway](https://www.assemblyai.com/docs/guides/counting-tokens.md)
### Voice AI Guides > Get quotes and citations with LLM Gateway
- [Extract Dialogue Data with LLM Gateway and JSON](https://www.assemblyai.com/docs/guides/dialogue-data.md)
- [Extract Quotes with Timestamps Using LLM Gateway + Semantic Search](https://www.assemblyai.com/docs/guides/transcript-citations.md)
- [Extract Transcript Quotes with LLM Gateway](https://www.assemblyai.com/docs/guides/timestamped-transcripts.md)
### Voice AI Guides > Substitute Speech Understanding with LLM Gateway
- [Analyze The Sentiment Of A Customer Call using LLM Gateway](https://www.assemblyai.com/docs/guides/call-sentiment-analysis.md)
- [Custom Topic Tags Using LLM Gateway](https://www.assemblyai.com/docs/guides/custom-topic-tags.md)
- [Redact PII from Text Using LLM Gateway](https://www.assemblyai.com/docs/guides/llm-gateway-pii-redaction.md)
### Voice AI Guides > Streaming with LLM Gateway
- [Apply LLM Gateway to Streaming](https://www.assemblyai.com/docs/guides/real_time_llm_gateway.md): Learn how to analyze streaming audio transcripts using LLM Gateway.
- [Translate Real-time STT Transcripts with LLM Gateway](https://www.assemblyai.com/docs/guides/real_time_translation.md)
### Voice AI Guides > Use-case specific LLM Gateway workflows
- [Implement a Sales Playbook Using LLM Gateway](https://www.assemblyai.com/docs/guides/sales-playbook.md)
- [Segment A Phone Call using LLM Gateway](https://www.assemblyai.com/docs/guides/phone-call-segmentation.md)
- [Generate SOAP Notes using LLM Gateway](https://www.assemblyai.com/docs/guides/soap-note-generation.md)

## FAQ

- [Frequently Asked Questions](https://www.assemblyai.com/docs/faq.md): Find answers to common questions about AssemblyAI's services, features, and pricing.
- [FAQ (part 1 of 2)](https://www.assemblyai.com/docs/llms-full/faq-1.txt): Every page in this section, with its URL.
- [FAQ (part 2 of 2)](https://www.assemblyai.com/docs/llms-full/faq-2.txt): Every page in this section, with its URL.

## Additional pages

- [AssemblyAI integration prompt for AI coding agents](https://www.assemblyai.com/docs/agent-instructions.md): The full integration prompt AI coding agents fetch when building with AssemblyAI.
- [Deployment](https://www.assemblyai.com/docs/deployment.md): Take AssemblyAI to production with these best practices.
- [Errors and limits](https://www.assemblyai.com/docs/errors.md): Every documented AssemblyAI error with its cause and fix, rate limits by plan, and links to the full error and limit...
- [\U0001F99C️\U0001F517 LangChain Integration with AssemblyAI](https://www.assemblyai.com/docs/integrations/langchain.md): Transcribe audio in LangChain using the built-in integration with AssemblyAI.
- [Select The EU Region for EU Data Residency](https://www.assemblyai.com/docs/pre-recorded-audio/guides/how_to_use_the_eu_endpoint.md)
- [Identifying speakers in audio recordings](https://www.assemblyai.com/docs/pre-recorded-audio/guides/identifying-speakers-in-audio-recordings.md): Add speaker labels to your transcript
- [Streaming v2 (Legacy)](https://www.assemblyai.com/docs/pre-recorded-audio/legacy-streaming.md): Transcribe live audio with Streaming Speech-to-Text
- [Universal-3.5 Pro](https://www.assemblyai.com/docs/pre-recorded-audio/universal-3-5-pro.md): Set up and configure Universal-3.5 Pro for pre-recorded audio transcription.
- [Tracking customer transcription usage](https://www.assemblyai.com/docs/tracking-your-customers-usage.md): Learn how to track individual customer usage within your product using AssemblyAI's webhook system and metadata.
- [Use case guides](https://www.assemblyai.com/docs/use-cases.md): Build real-world applications with AssemblyAI.
- [Universal-3.5 Pro Realtime API](https://www.assemblyai.com/docs/voice-agents/universal-3-5-pro-streaming-api.md): Build a custom voice agent on AssemblyAI's streaming WebSocket with turn detection, barge-in, and interruption...

## API specs

- [docs/openapi.yaml](https://www.assemblyai.com/docs/openapi.yaml): API specification source used by the docs.
- [docs/api-reference/specs/llm-gateway.yaml](https://www.assemblyai.com/docs/api-reference/specs/llm-gateway.yaml): API specification source used by the docs.
- [docs/api-reference/specs/streaming-token.yaml](https://www.assemblyai.com/docs/api-reference/specs/streaming-token.yaml): API specification source used by the docs.
- [docs/api-reference/specs/streaming.yaml](https://www.assemblyai.com/docs/api-reference/specs/streaming.yaml): API specification source used by the docs.
- [docs/api-reference/specs/streaming-tts.yaml](https://www.assemblyai.com/docs/api-reference/specs/streaming-tts.yaml): API specification source used by the docs.