{"schemaVersion":1,"profileUrl":"https://nowen.ai/agents/assemblyai-com","markdownUrl":"https://nowen.ai/agents/assemblyai-com.md","jsonUrl":"https://nowen.ai/agents/assemblyai-com.json","name":"AssemblyAI","website":"https://assemblyai.com","industry":"AI Infrastructure","deliveryModel":"software","marketCategories":{"primary":{"name":"MCP Servers","url":"https://nowen.ai/category/mcp-servers"},"others":[]},"status":{"trust":"unclaimed","text":"Unclaimed: compiled by Nowen from public sources, not reviewed by the company"},"updatedAt":"2026-11-12T16:52:16.733Z","summary":"AssemblyAI provides voice AI infrastructure that helps developers build applications for processing and understanding spoken conversations.","description":"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.","directory":{"industryName":"AI Infrastructure","agentCount":19,"indexable":true,"hubUrl":"https://nowen.ai/industry/ai-infrastructure"},"categoryDirectory":{"name":"MCP Servers","agentCount":83,"indexable":true,"url":"https://nowen.ai/category/mcp-servers"},"aiReaderFamilies":["OpenAI","Perplexity","Meta"],"boonFrontDoor":{"url":"https://boon.ai/agents/assemblyai-com","label":"Apply to AssemblyAI's partner program through Boon","sub":"Your AI agent writes the proposal: who you are, the fit, and a first step."},"nowenScore":{"value":63,"rangeLow":50,"rangeHigh":75,"tier":"measured","asOf":"2026-11-21"},"nowenScoreUrl":"https://nowen.ai/agents/assemblyai-com/score","products":[{"name":"Pre-recorded Speech-to-Text API","anchor":"product-pre-recorded-speech-to-text-api","type":"Product","url":"https://www.assemblyai.com/products/speech-to-text","summary":"Turn recorded speech into accurate, customizable transcripts and structured insights for applications and workflows.","description":"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.","pricing":{},"features":[{"name":"High-accuracy transcription models","value":"Transcribe Recorded Audio Accurately","valueDescription":"Select a model suited to the audio and workload, from complex domain-specific recordings to high-volume transcription."},{"name":"Multilingual transcription","value":"Transcribe Audio Across Languages","valueDescription":"Build multilingual transcription workflows using one API, with language coverage and code-switching support depending on the model."},{"name":"Speaker diarization","value":"Attribute Transcript Segments To Speakers","valueDescription":"Identify who said each utterance and when, making recorded conversations easier to review and analyze."},{"name":"Automatic language detection","value":"Detect Languages Automatically","valueDescription":"Avoid manual language selection and routing, with controls for expected languages and fallback behavior."},{"name":"Natural language prompting","value":"Guide Transcription With Context","valueDescription":"Supply contextual information to help the model handle terms and subject matter relevant to a recording."},{"name":"Keyterm prompting","value":"Improve Recognition Of Key Terms","valueDescription":"Emphasize relevant terminology in the request to support recognition of names and specialized vocabulary."},{"name":"Medical transcription mode","value":"Transcribe Medical Audio More Accurately","valueDescription":"Improve recognition of medical terminology in healthcare conversations and clinical recordings."},{"name":"Medical terminology recognition","value":"Recognize Clinical Terminology","valueDescription":"Improve transcription of specialized medical language in clinical recordings."},{"name":"Entity detection","value":"Extract Timestamped Entities","valueDescription":"Convert recognized entities into typed fields with timestamps for downstream use."},{"name":"PII redaction","value":"Redact Personal Information","valueDescription":"Reduce exposure of sensitive information by removing it from transcript text and, where enabled, bleeping it from audio."},{"name":"Speaker identification","value":"Identify Speakers By Name Or Role","valueDescription":"Associate speakers with names or roles using audio context."},{"name":"Summarization and chapters","value":"Summarize Recordings And Create Chapters","valueDescription":"Turn long recordings into concise summaries and timestamped sections that help users navigate the content."},{"name":"Action item extraction","value":"Extract Timestamped Action Items","valueDescription":"Identify follow-ups and return them with source quotes and timestamps."},{"name":"Sentiment analysis","value":"Classify Sentiment By Sentence","valueDescription":"Review how sentiment varies throughout a transcript, including by speaker when diarization is enabled."},{"name":"Content moderation","value":"Detect And Moderate Sensitive Content","valueDescription":"Identify sensitive content and clean up offensive language before transcript content is used downstream."},{"name":"Topic detection","value":"Classify Topics In Recordings","valueDescription":"Organize recorded audio by classifying its subject matter against standard IAB Content Taxonomy categories."},{"name":"Key phrase extraction","value":"Find Relevant Phrases With Timestamps","valueDescription":"Identify and rank important phrases, with timestamps to locate them in the audio."},{"name":"Custom transcript formatting","value":"Standardize Transcript Formatting","valueDescription":"Normalize common data formats so dates, phone numbers, currency, and URLs are ready for downstream systems."},{"name":"Transcript translation","value":"Translate Transcripts Into Other Languages","valueDescription":"Translate transcript text as part of the request and choose a formal or informal style."}]},{"name":"Realtime Speech-to-Text API","anchor":"product-realtime-speech-to-text-api","type":"Product","url":"https://www.assemblyai.com/products/streaming-speech-to-text","summary":"Turn live speech into fast, accurate transcripts for responsive voice applications, captions, and real-time assistance.","description":"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.","pricing":{},"features":[{"name":"Low-latency streaming transcription","value":"Get Live Transcripts Fast","valueDescription":"Receive text while a speaker is still talking, enabling responsive voice agents, live captions, and other applications that depend on timely transcripts."},{"name":"End-of-turn detection","value":"Detect When Speakers Finish","valueDescription":"Identify the end of a spoken turn so applications can respond promptly without relying only on pauses."},{"name":"Multilingual transcription","value":"Transcribe Across 32 Languages","valueDescription":"Support multilingual voice experiences with real-time models covering up to 32 languages and automatic language detection on supported models."},{"name":"Context carryover and conversation memory","value":"Carry Context Across Conversations","valueDescription":"Retain conversational context across an ongoing session to support more consistent realtime transcription."},{"name":"Keyterm and contextual prompting","value":"Boost Recognition Of Important Terms","valueDescription":"Guide supported models toward important names, terminology, and context so transcripts better fit the application or domain."},{"name":"Speaker diarization and labels","value":"Identify Speakers In Live Audio","valueDescription":"Separate spoken turns by speaker and label who said what during live conversations."},{"name":"Voice application integrations","value":"Connect To Existing Voice Stacks","valueDescription":"Integrate realtime transcription into supported orchestration frameworks and voice application stacks."},{"name":"Unlimited concurrent streams","value":"Scale With Unlimited Streams","valueDescription":"Run concurrent transcription streams without listed concurrency caps."},{"name":"Voice isolation","value":"Isolate Voices In Audio","valueDescription":"Use the supported model’s voice isolation capability to focus realtime transcription on speech."},{"name":"Automatic transcript formatting","value":"Format Transcripts Automatically","valueDescription":"Return readable live transcripts with automatic punctuation, casing, and supported formatting."},{"name":"Code-switching","value":"Handle Language Switching","valueDescription":"Transcribe supported multilingual conversations that switch between languages."},{"name":"Medical mode","value":"Recognize Medical Terminology","valueDescription":"Add Medical Mode to supported realtime models for clinical terminology recognition and noise-resilient transcription."}]},{"name":"Sync Speech-to-Text API","anchor":"product-sync-speech-to-text-api","type":"Product","url":"https://www.assemblyai.com/products/sync-speech-to-text","summary":"Get accurate transcripts from short audio clips in one fast request, without polling or managing a transcription session.","description":"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.","pricing":{},"features":[{"name":"Single-request transcription","value":"Get Transcripts In One Request","valueDescription":"Complete transcription in a single request-response call, avoiding job management and polling."},{"name":"Low-latency transcription","value":"Receive Finished Text In ~134 Ms","valueDescription":"Return a finished transcript quickly for dictation, push-to-talk commands, voicemail, and voice agents with their own turn detection."},{"name":"Universal-3.5 Pro accuracy","value":"Use Flagship Transcription Accuracy","valueDescription":"Get the stated Universal-3.5 Pro accuracy with a synchronous, single-request endpoint."},{"name":"Audio clip capacity","value":"Transcribe Clips Up To 20 Minutes","valueDescription":"Handle bounded audio clips in one request, including recordings up to 20 minutes."},{"name":"Per-word transcript metadata","value":"Use Word-Level Timing And Confidence","valueDescription":"Access timing and confidence alongside each word for applications that use detailed transcript information."},{"name":"Multilingual transcription","value":"Transcribe In 18 Supported Languages","valueDescription":"Build voice input for users of supported languages, including English, Spanish, French, German, Japanese, Mandarin, Hindi, and Turkish."},{"name":"Keyterms and conversation context","value":"Guide Transcription With Keyterms","valueDescription":"Use keyterms and conversation context to provide relevant information for transcription."}]},{"name":"Dictation API","anchor":"product-dictation-api","type":"Product","url":"https://www.assemblyai.com/products/dictation-api","summary":"Turn speech into accurate, ready-to-use text quickly, with customized formatting and a verbatim transcript included.","description":"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.","pricing":{},"features":[{"name":"Single-request transcription and cleanup","value":"Get Finished Text In One Call","valueDescription":"Send a spoken utterance and receive formatted, cleaned-up text in the same request."},{"name":"Automatic speech cleanup","value":"Clean Up Speech Automatically","valueDescription":"Return text with filler removed and punctuation and capitalization applied, while retaining the speaker’s phrasing and tone."},{"name":"Verbatim and rewritten text","value":"Access Both Text Versions","valueDescription":"Use the original words and finished rewrite from the same response, with the verbatim transcript separate from the rewrite."},{"name":"Custom rewrite instructions","value":"Format Text To Match Your Workflow","valueDescription":"Specify the structure or style an application needs, such as a clinical note."},{"name":"Low-latency responses","value":"Receive Text In Under A Second","valueDescription":"Get finished text quickly after a spoken utterance, supporting responsive voice input."},{"name":"Transcription context and key-term prompting","value":"Guide Recognition With Context And Terms","valueDescription":"Provide contextual guidance and important terms to help transcribe vocabulary relevant to a product or workflow."},{"name":"Multilingual dictation and code-switching","value":"Dictate Across 32 Languages","valueDescription":"Let users dictate in supported languages, including mixed-language speech, without manual language selection."},{"name":"Universal-3.5 Pro transcription","value":"Transcribe With Universal-3.5 Pro","valueDescription":"Use the Universal-3.5 Pro speech model for short-form dictation transcription."}]},{"name":"Speech Understanding API","anchor":"product-speech-understanding-api","type":"Product","url":"https://www.assemblyai.com/products/speech-understanding","summary":"Turn conversations into structured insights that help teams analyze, organize, and act on audio data.","description":"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.","pricing":{},"features":[{"name":"Single-request feature integration","value":"Combine Features In One Request","valueDescription":"Add multiple speech understanding capabilities to the same transcription request without building separate processing pipelines."},{"name":"Speaker diarization","value":"Separate Speakers In Transcripts","valueDescription":"Organize conversation audio into speaker-labeled segments with timestamps."},{"name":"Summarization and chapters","value":"Summarize And Organize Recordings","valueDescription":"Create concise summaries and timestamped sections that help people navigate and review recordings."},{"name":"Entity detection","value":"Extract Typed Entities With Timestamps","valueDescription":"Get structured entity data with categories and precise timestamps for downstream applications."},{"name":"PII redaction","value":"Redact Personal Information From Audio","valueDescription":"Remove personally identifiable information from transcript text and bleep it from audio in one API call."},{"name":"Speaker identification","value":"Identify Speakers By Name","valueDescription":"Attribute conversation segments to names or roles instead of generic speaker labels."},{"name":"Action item extraction","value":"Extract Timestamped Follow-Ups","valueDescription":"Surface follow-ups with timestamps and supporting quotes."},{"name":"Sentiment analysis","value":"Analyze Sentiment By Sentence","valueDescription":"Add sentence-level sentiment and, when speaker labels are enabled, connect results to individual speakers."},{"name":"Automatic language detection","value":"Detect And Transcribe 99 Languages","valueDescription":"Identify the dominant language and transcribe without manual selection, with options to restrict detection and set a fallback."},{"name":"Translation","value":"Translate Transcripts Into 86 Languages","valueDescription":"Produce translated transcripts in the same request and select a formal or informal style."},{"name":"Key phrase extraction","value":"Surface Relevant Phrases","valueDescription":"Find important concepts and phrases in recordings without manually searching raw transcripts."},{"name":"Topic detection","value":"Classify Audio Topics","valueDescription":"Categorize audio against standard IAB Content Taxonomy categories to organize and analyze recordings."},{"name":"Custom formatting","value":"Normalize Transcript Formatting","valueDescription":"Convert dates, phone numbers, currency, and URLs into standardized formats."},{"name":"Content moderation","value":"Detect Sensitive And Offensive Content","valueDescription":"Identify sensitive content and clean up offensive language automatically."}]},{"name":"Guardrails API","anchor":"product-guardrails-api","type":"Product","url":"https://www.assemblyai.com/products/guardrails","summary":"Protect voice data and keep transcription outputs clean with built-in privacy, safety, and operational controls.","description":"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.","pricing":{},"features":[{"name":"PII text redaction","value":"Remove Sensitive Data From Transcripts","valueDescription":"Redact personal information in transcript text within the transcription request, helping reduce sensitive data in downstream systems and support privacy and compliance workflows."},{"name":"PII audio redaction","value":"Bleep Personal Information In Audio","valueDescription":"Create audio with sensitive spans bleeped in the same request, supporting safer storage, sharing, and compliance archiving."},{"name":"Content moderation","value":"Flag Sensitive Content Against Your Policy","valueDescription":"Identify potentially sensitive material and review flagged text, timestamps, confidence, and severity to support content review and policy enforcement."},{"name":"Profanity filtering","value":"Clean Profanity From Transcripts","valueDescription":"Automatically filter offensive language from transcription output to help keep content clean."},{"name":"Speech threshold","value":"Transcribe Only Files With Enough Speech","valueDescription":"Use a minimum spoken-audio threshold to validate whether an input should be transcribed."},{"name":"Transcript start and end controls","value":"Limit Transcription To Spoken Sections","valueDescription":"Set transcript start and end controls to focus on sections containing speech."}]},{"name":"LLM Gateway","anchor":"product-llm-gateway","type":"Product","url":"https://www.assemblyai.com/products/llm-gateway","summary":"Apply and compare language models on voice data and transcripts through one API, with model choice, provider rates, and task-specific options.","description":"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.","pricing":{},"features":[{"name":"Unified model access","value":"Access Multiple Models Through One API","valueDescription":"Use one interface to apply different language models to voice data and transcripts across supported providers."},{"name":"Model and provider selection","value":"Choose Models For Your Workflows","valueDescription":"Compare model options and select based on published capabilities, task recommendations, pricing, provider, and available region."},{"name":"OpenAI-compatible API","value":"Integrate With An OpenAI-Compatible API","valueDescription":"Connect existing SDK workflows and switch the selected model by changing its identifier."},{"name":"Transcript task support","value":"Process Transcripts For Different Tasks","valueDescription":"Choose models for transcript workflows such as cleanup, extraction, summarization, correction, generation, and formatting."},{"name":"Shared Speech-to-Text API key","value":"Use One Key For Speech And LLMs","valueDescription":"Use the same API key for Speech-to-Text and LLM Gateway requests."},{"name":"Automatic model fallbacks","value":"Enable Automatic Model Fallbacks","valueDescription":"Use the Gateway’s automatic fallback capability when working with supported models."},{"name":"Provider-rate pricing","value":"Pay Provider Rates With No Markup","valueDescription":"Pay selected model provider rates without Gateway markup, based on input and output tokens and with no minimum commitment."},{"name":"Model catalog comparison","value":"Compare Model Details Before Choosing","valueDescription":"Review model context, costs, capabilities, supported tasks, providers, and regions to inform selection."},{"name":"Zero data retention for eligible models","value":"Use Zero Retention For Eligible Models","valueDescription":"For Anthropic and Google models under a signed BAA, the Gateway offers zero data retention."},{"name":"Regional model availability","value":"Select Models By Available Region","valueDescription":"Compare listed regions and choose available US, EU, or global options where supported."}]},{"name":"Text-to-Speech API","anchor":"product-text-to-speech-api","type":"Product","url":"https://www.assemblyai.com/products/text-to-speech","summary":"Create natural, fast voice-agent responses that keep callers engaged and scale with call volume.","description":"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.","pricing":{},"features":[{"name":"Natural conversational speech","value":"Create More Natural Voice-Agent Conversations","valueDescription":"Generate speech designed for real conversations, helping voice agents sound more natural on live calls."},{"name":"Low-latency audio streaming","value":"Start Speaking From The First Byte","valueDescription":"Begin streaming audio quickly so voice agents can respond sooner during live calls."},{"name":"Scalable concurrency","value":"Scale Calls Without Concurrency Limits","valueDescription":"Scale concurrency with call volume to accommodate call spikes without negotiating a commitment."},{"name":"Instant voice cloning","value":"Clone A Voice From A 30-Second Clip","valueDescription":"Create a branded agent voice from a short audio clip, with permission confirmed at upload."},{"name":"Multilingual speech generation","value":"Speak Across Six Supported Languages","valueDescription":"Build voice agents that speak six supported languages with the appropriate accent for the selected language."},{"name":"Multilingual voice library","value":"Choose From Thousands Of Voices","valueDescription":"Explore and audition voices across languages, accents, and regions."},{"name":"Flexible integration options","value":"Integrate Through Frameworks Or APIs","valueDescription":"Connect through LiveKit or Pipecat, or use HTTP or WebSocket for a custom integration."}]},{"name":"Voice AI Cloud","anchor":"product-voice-ai-cloud","type":"Platform","url":"https://www.assemblyai.com/deployments/cloud","summary":"Build and scale production Voice AI applications through a managed API, without managing GPUs, infrastructure, or capacity planning.","description":"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.","pricing":{},"features":[{"name":"Managed inference","value":"Run Models Without Managing Infrastructure","valueDescription":"Use managed inference instead of building and operating model-serving infrastructure or provisioning GPUs."},{"name":"Elastic concurrency","value":"Scale From Zero To Thousands Of Streams","valueDescription":"Adjust capacity automatically as voice traffic changes, supporting production workloads and spikes without capacity planning or GPU provisioning."},{"name":"Reliability and failover","value":"Maintain Resilient Production Workloads","valueDescription":"Rely on the stated uptime SLA, multi-region redundancy, and automatic failover for production applications."},{"name":"Single API and SDKs","value":"Build Voice Apps Through One API","valueDescription":"Integrate managed inference and AssemblyAI models through a single API and available SDKs."},{"name":"Usage-based pricing","value":"Pay Only For Usage","valueDescription":"Use per-second pricing without minimum commitments or long-term contracts, paying for usage rather than over-provisioned capacity."},{"name":"Security and compliance support","value":"Support Enterprise Compliance Requirements","valueDescription":"Use cloud infrastructure with SOC 2 and GDPR support without additional customer-side setup."},{"name":"Hands-off infrastructure operations","value":"Skip Infrastructure Maintenance","valueDescription":"Avoid managing capacity planning and infrastructure updates; AssemblyAI handles scaling, reliability, and infrastructure optimizations."}]},{"name":"Self-Hosted Voice AI","anchor":"product-self-hosted-voice-ai","type":"Platform","url":"https://www.assemblyai.com/deployments/self-hosted","summary":"Run AssemblyAI speech-to-text in your own environment to keep audio under your control, meet residency requirements, and reduce network latency.","description":"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.","pricing":{},"features":[{"name":"Self-hosted model deployment","value":"Run Models In Your Environment","valueDescription":"Deploy AssemblyAI models within your infrastructure, keeping the voice processing stack close to your applications and under your operational control."},{"name":"Data sovereignty and residency","value":"Keep Audio Within Your Perimeter","valueDescription":"Process audio inside your controlled environment to retain data sovereignty and address regulatory and data residency requirements."},{"name":"Realtime and sync speech-to-text APIs","value":"Transcribe Live Streams And Short Clips","valueDescription":"Choose realtime streaming for live audio or the Sync API for short clips, with both running inside your environment."},{"name":"Local processing latency","value":"Reduce Latency Near Your Traffic","valueDescription":"Run processing closer to users and infrastructure; the site reports potential latency reductions of 50–200 ms in regions far from cloud endpoints."},{"name":"Infrastructure control and observability","value":"Tune Scaling To Your Traffic","valueDescription":"Adjust deployment scaling to fit traffic patterns and use provided metrics and observability to support autoscaling."},{"name":"Container orchestration support","value":"Deploy On Your Orchestration Platform","valueDescription":"Use Kubernetes, AWS ECS, or another existing platform, with a Docker Compose demo and engineering assistance for production deployments."},{"name":"Usage-based session pricing","value":"Pay For Active Sessions","valueDescription":"Use cloud-equivalent usage-based pricing without a self-hosting premium, with daily billing and volume discounts available."},{"name":"GPU configuration flexibility","value":"Choose A Supported GPU Configuration","valueDescription":"Select from supported GPU configurations; the deployment page states each instance handles up to 48 concurrent streams without runtime degradation."},{"name":"Cloud provider committed-spend integration","value":"Apply Usage To AWS Commitments","valueDescription":"Run an AssemblyAI agreement through AWS Marketplace so eligible usage counts toward AWS committed spend."}]},{"name":"Blurt","anchor":"product-blurt","type":"Product","url":"https://www.assemblyai.com/blurt","summary":"Dictate naturally and get cleaned-up text inserted into the app you’re using, with multiple languages and writing styles supported.","description":"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.","pricing":{},"features":[{"name":"System-wide hotkey dictation","value":"Dictate Into Any Focused App","valueDescription":"Capture speech with a hotkey and have text appear in the active text field across the apps you already use."},{"name":"Automatic text cleanup","value":"Turn Speech Into Clean Text","valueDescription":"Speak naturally, including filler words or corrections, and get cleaned-up text ready to use."},{"name":"Custom writing styles","value":"Match Text To Your Style","valueDescription":"Choose or define a writing style for the context, such as a casual message or formal email."},{"name":"Fast transcription","value":"Get Dictation Back Quickly","valueDescription":"Fast transcription and cleanup help text appear promptly after speaking, without waiting on a job queue."},{"name":"Transcription accuracy","value":"Capture Speech More Accurately","valueDescription":"Designed to handle accents, code, and domain jargon; the product page claims up to 30% fewer hallucinations than Whisper."},{"name":"Open-source MIT license","value":"Fork And Customize The App","valueDescription":"Fork and modify the MIT-licensed source. Blurt is free to use, but users provide their own API key and pay for transcription usage."},{"name":"Multilingual dictation","value":"Dictate Across 19 Languages","valueDescription":"Speak in supported languages and switch mid-sentence; Blurt follows language changes without a setting change."},{"name":"Custom vocabulary","value":"Spell Specialized Terms Correctly","valueDescription":"Add product names, acronyms, and function names to custom vocabulary to help them come out correctly."}]},{"name":"AssemblyAI MCP Server","anchor":"product-assemblyai-mcp-server","type":"Product","url":"https://www.assemblyai.com/docs/mcp-server","summary":"Transcribe, summarize, and analyze audio from compatible AI clients using an AssemblyAI account, without writing code for the task.","description":"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.","pricing":{},"features":[{"name":"MCP client integration","value":"Connect AI Clients To AssemblyAI","valueDescription":"Use supported MCP clients to access AssemblyAI audio transcription and analysis tools through the remote server."},{"name":"Audio transcription","value":"Transcribe Audio From An MCP Client","valueDescription":"Submit audio for transcription through an MCP client connected to the user’s AssemblyAI account."},{"name":"Account authentication","value":"Authenticate With OAuth Or An API Key","valueDescription":"Choose OAuth sign-in or API-key authorization to connect the MCP client to the user’s account."},{"name":"Transcript summarization","value":"Summarize Transcripts In Your Account","valueDescription":"Request transcript summaries through a compatible MCP client using audio processed on the user’s account."},{"name":"Transcript analysis","value":"Analyze Transcripts Through MCP","valueDescription":"Run transcript analysis through an MCP client using the understand_transcript tool."},{"name":"Transcript retrieval","value":"Retrieve Transcripts Through MCP","valueDescription":"Get transcript results from the user’s account through a compatible MCP client."},{"name":"Transcript deletion","value":"Delete Transcripts From Your Account","valueDescription":"Use the delete_transcript tool to remove transcripts from the user’s account."},{"name":"API-rate billing","value":"Pay At Normal API Rates","valueDescription":"MCP server usage follows AssemblyAI’s normal API-rate billing."}],"marketCategories":[{"name":"MCP Servers","url":"https://nowen.ai/category/mcp-servers"}]},{"name":"Docs MCP Server","anchor":"product-docs-mcp-server","type":"Product","url":"https://www.assemblyai.com/docs/mcp","summary":"Helps coding agents find current AssemblyAI documentation and write more accurate integration code.","description":"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.","pricing":{},"features":[{"name":"Documentation search and reading","value":"Find And Read Current Documentation","valueDescription":"Lets coding agents search and read live documentation to use relevant information when generating code."},{"name":"Coding-agent compatibility","value":"Connect Coding Agents To AssemblyAI Docs","valueDescription":"Provides coding agents access to AssemblyAI documentation through MCP, supporting more accurate integration code."},{"name":"Free, unauthenticated access","value":"Access Docs Without Cost Or Authentication","valueDescription":"Coding agents can use the documentation server without a fee or authentication."}],"marketCategories":[{"name":"MCP Servers","url":"https://nowen.ai/category/mcp-servers"}]},{"name":"AssemblyAI Playground","anchor":"product-assemblyai-playground","type":"Platform","url":"https://www.assemblyai.com/playground","summary":"Test AssemblyAI Voice AI models on audio without code and explore transcription, speaker identification, and speech understanding features.","description":"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.","pricing":{},"features":[{"name":"No-code Voice AI testing","value":"Test Voice AI Models Without Code","valueDescription":"Try AssemblyAI Voice AI models in a browser-based playground without writing code."},{"name":"Transcription model and context controls","value":"Configure Models And Transcription","valueDescription":"Adjust model and transcription settings, including prompts, key terms, and specialized modes, to test audio with different contexts."},{"name":"Audio sample and input options","value":"Test Audio From Multiple Sources","valueDescription":"Choose a supplied sample, upload audio, or enter a URL to explore model behavior across inputs and scenarios."},{"name":"Multilingual transcription","value":"Test Transcription Across 18 Languages","valueDescription":"Explore transcription in 18 languages, including native code-switching, and use automatic language detection."},{"name":"Speaker and channel controls","value":"Explore Speaker And Channel Settings","valueDescription":"Test speaker-related options, including diarization, labels, identification, multichannel audio, and automatic detection."},{"name":"Audio summarization","value":"Summarize Audio","valueDescription":"Explore the summarization option to turn audio into a summary in the playground."},{"name":"PII redaction","value":"Try PII Redaction","valueDescription":"Test PII redaction as part of the playground’s speech understanding features."},{"name":"Sentiment analysis","value":"Explore Audio Sentiment","valueDescription":"Try sentiment analysis on audio using the playground’s speech understanding options."},{"name":"Audio translation","value":"Try Audio Translation","valueDescription":"Explore translation through the playground’s speech understanding controls."},{"name":"Topic detection","value":"Explore Audio Topics","valueDescription":"Test topic detection as part of the playground’s speech understanding options."},{"name":"Content moderation","value":"Test Content Moderation","valueDescription":"Explore content moderation through the playground’s speech understanding controls."},{"name":"Profanity filtering","value":"Test Profanity Filtering","valueDescription":"Explore profanity filtering through the playground’s speech understanding controls."},{"name":"Action item extraction","value":"Identify Action Items","valueDescription":"Try the action items option among the playground’s speech understanding features."}]}],"audiences":[],"segments":[],"faq":[],"comparisons":[],"sources":[{"url":"https://assemblyai.com","text":"AssemblyAI"},{"url":"https://www.assemblyai.com/products/speech-to-text","text":"Pre-recorded Speech-to-Text API"},{"url":"https://www.assemblyai.com/products/streaming-speech-to-text","text":"Realtime Speech-to-Text API"},{"url":"https://www.assemblyai.com/products/sync-speech-to-text","text":"Sync Speech-to-Text API"},{"url":"https://www.assemblyai.com/products/dictation-api","text":"Dictation API"},{"url":"https://www.assemblyai.com/products/speech-understanding","text":"Speech Understanding API"},{"url":"https://www.assemblyai.com/products/guardrails","text":"Guardrails API"},{"url":"https://www.assemblyai.com/products/llm-gateway","text":"LLM Gateway"},{"url":"https://www.assemblyai.com/products/text-to-speech","text":"Text-to-Speech API"},{"url":"https://www.assemblyai.com/deployments/cloud","text":"Voice AI Cloud"},{"url":"https://www.assemblyai.com/deployments/self-hosted","text":"Self-Hosted Voice AI"},{"url":"https://www.assemblyai.com/blurt","text":"Blurt"},{"url":"https://www.assemblyai.com/docs/mcp-server","text":"AssemblyAI MCP Server"},{"url":"https://www.assemblyai.com/docs/mcp","text":"Docs MCP Server"},{"url":"https://www.assemblyai.com/playground","text":"AssemblyAI Playground"}]}