# AssemblyAI

- Status: Unclaimed: compiled by Nowen from public sources, not reviewed by the company
- Industry: AI Infrastructure
- Market category: MCP Servers (https://nowen.ai/category/mcp-servers)
- Delivery model: software
- Website: https://assemblyai.com
- AI agent profile: https://nowen.ai/agents/assemblyai-com
- Front door on Boon: https://boon.ai/agents/assemblyai-com (Apply to AssemblyAI's partner program through Boon)
- Updated: 2026-11-12
- Nowen Score: 63 (range 50–75, measured, as of 2026-11-21). What it means: https://nowen.ai/agents/assemblyai-com/score
- Directory: one of 19 AI agents in AI Infrastructure (https://nowen.ai/industry/ai-infrastructure); one of 83 AI agents in MCP Servers (https://nowen.ai/category/mcp-servers)
- Read by AI assistants from: OpenAI, Perplexity, Meta

> AssemblyAI provides voice AI infrastructure that helps developers build applications for processing and understanding spoken conversations.

AssemblyAI provides voice AI infrastructure for developers and organizations building voice-enabled applications. Its capabilities help teams convert speech into text, derive structured insights from conversations, and create natural spoken interactions, with tools for deployment, security, and compliance.

**Mission:** Help developers build voice-enabled products by making voice AI capabilities accessible, reliable, and scalable.

## Products & Services

### [Pre-recorded Speech-to-Text API](https://www.assemblyai.com/products/speech-to-text)
*Product*
Turn recorded speech into accurate, customizable transcripts and structured insights for applications and workflows.
AssemblyAI’s Pre-recorded Speech-to-Text API converts recorded audio into clean, customizable transcripts and structured insights. Choose Universal-3.5 Pro for complex, domain-specific audio or Universal-2 for high-volume transcription across 99 languages. Add speaker labeling, language detection, prompting, medical transcription, summarization, sentiment analysis, entity detection, and PII redaction to requests.

- **High-accuracy transcription models** — Transcribe Recorded Audio Accurately
- **Multilingual transcription** — Transcribe Audio Across Languages
- **Speaker diarization** — Attribute Transcript Segments To Speakers
- **Automatic language detection** — Detect Languages Automatically
- **Natural language prompting** — Guide Transcription With Context
- **Keyterm prompting** — Improve Recognition Of Key Terms
- **Medical transcription mode** — Transcribe Medical Audio More Accurately
- **Medical terminology recognition** — Recognize Clinical Terminology
- **Entity detection** — Extract Timestamped Entities
- **PII redaction** — Redact Personal Information
- **Speaker identification** — Identify Speakers By Name Or Role
- **Summarization and chapters** — Summarize Recordings And Create Chapters
- **Action item extraction** — Extract Timestamped Action Items
- **Sentiment analysis** — Classify Sentiment By Sentence
- **Content moderation** — Detect And Moderate Sensitive Content
- **Topic detection** — Classify Topics In Recordings
- **Key phrase extraction** — Find Relevant Phrases With Timestamps
- **Custom transcript formatting** — Standardize Transcript Formatting
- **Transcript translation** — Translate Transcripts Into Other Languages

### [Realtime Speech-to-Text API](https://www.assemblyai.com/products/streaming-speech-to-text)
*Product*
Turn live speech into fast, accurate transcripts for responsive voice applications, captions, and real-time assistance.
A streaming API that transcribes live audio and video into partial and final text for voice agents, live captions, notetakers, agent assist, and other real-time applications. Its models offer low-latency transcription. Universal-3.6 Pro Realtime supports 32 languages and features including turn detection, speaker labels, context carryover, and keyterm prompting.

- **Low-latency streaming transcription** — Get Live Transcripts Fast
- **End-of-turn detection** — Detect When Speakers Finish
- **Multilingual transcription** — Transcribe Across 32 Languages
- **Context carryover and conversation memory** — Carry Context Across Conversations
- **Keyterm and contextual prompting** — Boost Recognition Of Important Terms
- **Speaker diarization and labels** — Identify Speakers In Live Audio
- **Voice application integrations** — Connect To Existing Voice Stacks
- **Unlimited concurrent streams** — Scale With Unlimited Streams
- **Voice isolation** — Isolate Voices In Audio
- **Automatic transcript formatting** — Format Transcripts Automatically
- **Code-switching** — Handle Language Switching
- **Medical mode** — Recognize Medical Terminology

### [Sync Speech-to-Text API](https://www.assemblyai.com/products/sync-speech-to-text)
*Product*
Get accurate transcripts from short audio clips in one fast request, without polling or managing a transcription session.
A synchronous speech-to-text API for short audio clips. Send audio in one HTTP request and receive a finished transcript in the same response, typically in about 134 ms at P50. Built on Universal-3.5 Pro, it supports clips up to 20 minutes and 40 MB, with per-word text, timing, and confidence in every response. Keyterms and conversation context are supported.

- **Single-request transcription** — Get Transcripts In One Request
- **Low-latency transcription** — Receive Finished Text In ~134 Ms
- **Universal-3.5 Pro accuracy** — Use Flagship Transcription Accuracy
- **Audio clip capacity** — Transcribe Clips Up To 20 Minutes
- **Per-word transcript metadata** — Use Word-Level Timing And Confidence
- **Multilingual transcription** — Transcribe In 18 Supported Languages
- **Keyterms and conversation context** — Guide Transcription With Keyterms

### [Dictation API](https://www.assemblyai.com/products/dictation-api)
*Product*
Turn speech into accurate, ready-to-use text quickly, with customized formatting and a verbatim transcript included.
The Dictation API turns a spoken utterance into finished, formatted text in a single request. It combines transcription with an LLM cleanup pass, returning the verbatim transcript alongside cleaned-up text. Developers can customize transcription with context and key terms, and shape rewritten output with formatting instructions. It supports 32 languages with automatic language detection and code-switching, and returns finished text in under a second.

- **Single-request transcription and cleanup** — Get Finished Text In One Call
- **Automatic speech cleanup** — Clean Up Speech Automatically
- **Verbatim and rewritten text** — Access Both Text Versions
- **Custom rewrite instructions** — Format Text To Match Your Workflow
- **Low-latency responses** — Receive Text In Under A Second
- **Transcription context and key-term prompting** — Guide Recognition With Context And Terms
- **Multilingual dictation and code-switching** — Dictate Across 32 Languages
- **Universal-3.5 Pro transcription** — Transcribe With Universal-3.5 Pro

### [Speech Understanding API](https://www.assemblyai.com/products/speech-understanding)
*Product*
Turn conversations into structured insights that help teams analyze, organize, and act on audio data.
Turn raw audio into structured intelligence with purpose-built speech models in a single API call. Combine transcription with features that identify speakers, extract entities and action items, analyze sentiment and topics, summarize recordings, translate transcripts, and redact sensitive information. Choose the features needed without building separate processing pipelines.

- **Single-request feature integration** — Combine Features In One Request
- **Speaker diarization** — Separate Speakers In Transcripts
- **Summarization and chapters** — Summarize And Organize Recordings
- **Entity detection** — Extract Typed Entities With Timestamps
- **PII redaction** — Redact Personal Information From Audio
- **Speaker identification** — Identify Speakers By Name
- **Action item extraction** — Extract Timestamped Follow-Ups
- **Sentiment analysis** — Analyze Sentiment By Sentence
- **Automatic language detection** — Detect And Transcribe 99 Languages
- **Translation** — Translate Transcripts Into 86 Languages
- **Key phrase extraction** — Surface Relevant Phrases
- **Topic detection** — Classify Audio Topics
- **Custom formatting** — Normalize Transcript Formatting
- **Content moderation** — Detect Sensitive And Offensive Content

### [Guardrails API](https://www.assemblyai.com/products/guardrails)
*Product*
Protect voice data and keep transcription outputs clean with built-in privacy, safety, and operational controls.
Guardrails provides safety, privacy, and compliance controls at the transcription layer through one API. It can redact personally identifiable information from transcript text and audio, moderate sensitive content, filter profanity, and apply speech threshold and transcript start/end controls. It supports GDPR and PCI programs, with a BAA available for customers processing PHI.

- **PII text redaction** — Remove Sensitive Data From Transcripts
- **PII audio redaction** — Bleep Personal Information In Audio
- **Content moderation** — Flag Sensitive Content Against Your Policy
- **Profanity filtering** — Clean Profanity From Transcripts
- **Speech threshold** — Transcribe Only Files With Enough Speech
- **Transcript start and end controls** — Limit Transcription To Spoken Sections

### [LLM Gateway](https://www.assemblyai.com/products/llm-gateway)
*Product*
Apply and compare language models on voice data and transcripts through one API, with model choice, provider rates, and task-specific options.
LLM Gateway provides unified access to open and frontier language models through one API for voice data and transcripts. Use more than 50 models from multiple providers for dictation, information extraction, summarization, and text correction. Requests use an OpenAI-compatible interface, and the Gateway shares an API key with AssemblyAI Speech-to-Text. Compare model context, pricing, capabilities, tasks, providers, and regions, and switch models by changing a model identifier.

- **Unified model access** — Access Multiple Models Through One API
- **Model and provider selection** — Choose Models For Your Workflows
- **OpenAI-compatible API** — Integrate With An OpenAI-Compatible API
- **Transcript task support** — Process Transcripts For Different Tasks
- **Shared Speech-to-Text API key** — Use One Key For Speech And LLMs
- **Automatic model fallbacks** — Enable Automatic Model Fallbacks
- **Provider-rate pricing** — Pay Provider Rates With No Markup
- **Model catalog comparison** — Compare Model Details Before Choosing
- **Zero data retention for eligible models** — Use Zero Retention For Eligible Models
- **Regional model availability** — Select Models By Available Region

### [Text-to-Speech API](https://www.assemblyai.com/products/text-to-speech)
*Product*
Create natural, fast voice-agent responses that keep callers engaged and scale with call volume.
AssemblyAI-TTS-1 converts text into natural-sounding speech for voice agents and live calls. Trained on millions of hours of audio, including real conversations, it streams audio from the first byte, supports six languages, and offers a voice library and instant voice cloning. The API is designed for low-latency responses and concurrency that scales with call volume. Use it with LiveKit or Pipecat, or build an integration over HTTP or WebSocket.

- **Natural conversational speech** — Create More Natural Voice-Agent Conversations
- **Low-latency audio streaming** — Start Speaking From The First Byte
- **Scalable concurrency** — Scale Calls Without Concurrency Limits
- **Instant voice cloning** — Clone A Voice From A 30-Second Clip
- **Multilingual speech generation** — Speak Across Six Supported Languages
- **Multilingual voice library** — Choose From Thousands Of Voices
- **Flexible integration options** — Integrate Through Frameworks Or APIs

### [Voice AI Cloud](https://www.assemblyai.com/deployments/cloud)
*Platform*
Build and scale production Voice AI applications through a managed API, without managing GPUs, infrastructure, or capacity planning.
Voice AI Cloud is AssemblyAI’s managed inference platform for production Voice AI applications. It provides access to AssemblyAI models through an API and SDKs, with infrastructure that scales automatically from zero to thousands of concurrent streams. AssemblyAI handles model serving, GPU provisioning, capacity planning, reliability, and infrastructure updates. The service offers usage-based, per-second pricing with no minimums or long-term contracts, a 99.9% uptime SLA, multi-region redundancy, automatic failover, and SOC 2 and GDPR support.

- **Managed inference** — Run Models Without Managing Infrastructure
- **Elastic concurrency** — Scale From Zero To Thousands Of Streams
- **Reliability and failover** — Maintain Resilient Production Workloads
- **Single API and SDKs** — Build Voice Apps Through One API
- **Usage-based pricing** — Pay Only For Usage
- **Security and compliance support** — Support Enterprise Compliance Requirements
- **Hands-off infrastructure operations** — Skip Infrastructure Maintenance

### [Self-Hosted Voice AI](https://www.assemblyai.com/deployments/self-hosted)
*Platform*
Run AssemblyAI speech-to-text in your own environment to keep audio under your control, meet residency requirements, and reduce network latency.
Run AssemblyAI speech-to-text models within your own infrastructure, including a VPC, on-premises environment, or supported container orchestration platform. Keep audio inside your controlled perimeter while managing deployment and scaling to suit your traffic. Self-hosted deployments provide the Realtime Speech-to-Text API with Universal-3.5 Pro Realtime and the Sync Speech-to-Text API powered by Universal-3.5 Pro. Pricing is usage-based, matching the cloud service with no self-hosting premium.

- **Self-hosted model deployment** — Run Models In Your Environment
- **Data sovereignty and residency** — Keep Audio Within Your Perimeter
- **Realtime and sync speech-to-text APIs** — Transcribe Live Streams And Short Clips
- **Local processing latency** — Reduce Latency Near Your Traffic
- **Infrastructure control and observability** — Tune Scaling To Your Traffic
- **Container orchestration support** — Deploy On Your Orchestration Platform
- **Usage-based session pricing** — Pay For Active Sessions
- **GPU configuration flexibility** — Choose A Supported GPU Configuration
- **Cloud provider committed-spend integration** — Apply Usage To AWS Commitments

### [Blurt](https://www.assemblyai.com/blurt)
*Product*
Dictate naturally and get cleaned-up text inserted into the app you’re using, with multiple languages and writing styles supported.
Blurt is a free, open-source dictation app for macOS 14 and later. Hold a keyboard shortcut, speak, and Blurt inserts text into the focused app. It uses AssemblyAI’s Dictation API to transcribe and clean up text, removing filler words and resolving self-corrections. Users can choose or define writing styles, dictate in 19 languages, and code-switch mid-sentence. Blurt is MIT licensed; users provide their own AssemblyAI API key, and transcription usage is billed separately.

- **System-wide hotkey dictation** — Dictate Into Any Focused App
- **Automatic text cleanup** — Turn Speech Into Clean Text
- **Custom writing styles** — Match Text To Your Style
- **Fast transcription** — Get Dictation Back Quickly
- **Transcription accuracy** — Capture Speech More Accurately
- **Open-source MIT license** — Fork And Customize The App
- **Multilingual dictation** — Dictate Across 19 Languages
- **Custom vocabulary** — Spell Specialized Terms Correctly

### [AssemblyAI MCP Server](https://www.assemblyai.com/docs/mcp-server)
*Product*
Transcribe, summarize, and analyze audio from compatible AI clients using an AssemblyAI account, without writing code for the task.
AssemblyAI MCP Server is a remote Streamable HTTP server that connects MCP-compatible clients to a user’s AssemblyAI account. Clients can submit and retrieve transcripts, summarize and analyze audio, and delete transcripts using AssemblyAI tools. Connect at https://mcp.assemblyai.com/mcp and authenticate with AssemblyAI OAuth sign-in or an API key. Usage is billed at normal API rates.
- Categories: MCP Servers (https://nowen.ai/category/mcp-servers)

- **MCP client integration** — Connect AI Clients To AssemblyAI
- **Audio transcription** — Transcribe Audio From An MCP Client
- **Account authentication** — Authenticate With OAuth Or An API Key
- **Transcript summarization** — Summarize Transcripts In Your Account
- **Transcript analysis** — Analyze Transcripts Through MCP
- **Transcript retrieval** — Retrieve Transcripts Through MCP
- **Transcript deletion** — Delete Transcripts From Your Account
- **API-rate billing** — Pay At Normal API Rates

### [Docs MCP Server](https://www.assemblyai.com/docs/mcp)
*Product*
Helps coding agents find current AssemblyAI documentation and write more accurate integration code.
A free, unauthenticated MCP server that gives coding agents access to AssemblyAI’s live documentation. It searches and reads the docs to help agents such as Claude Code and Cursor write correct AssemblyAI code.
- Categories: MCP Servers (https://nowen.ai/category/mcp-servers)

- **Documentation search and reading** — Find And Read Current Documentation
- **Coding-agent compatibility** — Connect Coding Agents To AssemblyAI Docs
- **Free, unauthenticated access** — Access Docs Without Cost Or Authentication

### [AssemblyAI Playground](https://www.assemblyai.com/playground)
*Platform*
Test AssemblyAI Voice AI models on audio without code and explore transcription, speaker identification, and speech understanding features.
AssemblyAI Playground is a no-code environment for testing Voice AI models on audio. Choose a sample, upload an audio file, or provide a URL, then configure transcription and speech understanding options. The playground supports model selection, language detection, prompts, key terms, speaker settings, and analysis features including translation, topic detection, moderation, PII redaction, sentiment analysis, summarization, and action items.

- **No-code Voice AI testing** — Test Voice AI Models Without Code
- **Transcription model and context controls** — Configure Models And Transcription
- **Audio sample and input options** — Test Audio From Multiple Sources
- **Multilingual transcription** — Test Transcription Across 18 Languages
- **Speaker and channel controls** — Explore Speaker And Channel Settings
- **Audio summarization** — Summarize Audio
- **PII redaction** — Try PII Redaction
- **Sentiment analysis** — Explore Audio Sentiment
- **Audio translation** — Try Audio Translation
- **Topic detection** — Explore Audio Topics
- **Content moderation** — Test Content Moderation
- **Profanity filtering** — Test Profanity Filtering
- **Action item extraction** — Identify Action Items

## Sources

- [AssemblyAI](https://assemblyai.com)
- [Pre-recorded Speech-to-Text API](https://www.assemblyai.com/products/speech-to-text)
- [Realtime Speech-to-Text API](https://www.assemblyai.com/products/streaming-speech-to-text)
- [Sync Speech-to-Text API](https://www.assemblyai.com/products/sync-speech-to-text)
- [Dictation API](https://www.assemblyai.com/products/dictation-api)
- [Speech Understanding API](https://www.assemblyai.com/products/speech-understanding)
- [Guardrails API](https://www.assemblyai.com/products/guardrails)
- [LLM Gateway](https://www.assemblyai.com/products/llm-gateway)
- [Text-to-Speech API](https://www.assemblyai.com/products/text-to-speech)
- [Voice AI Cloud](https://www.assemblyai.com/deployments/cloud)
- [Self-Hosted Voice AI](https://www.assemblyai.com/deployments/self-hosted)
- [Blurt](https://www.assemblyai.com/blurt)
- [AssemblyAI MCP Server](https://www.assemblyai.com/docs/mcp-server)
- [Docs MCP Server](https://www.assemblyai.com/docs/mcp)
- [AssemblyAI Playground](https://www.assemblyai.com/playground)
