A

AssemblyAI Speech Understanding API

API service

by AssemblyAI

Add-on models switched on in a transcription request that turn recorded audio into structured output: speaker labels, sentiment, entities, topics, key phrases, summaries, translation and custom formatting, each priced per audio hour.

Find alternatives to AssemblyAI Speech Understanding API

What it does

• Summarization
• Translation

Features 7

• Speaker identificationLabels speakers by name using audio context, with custom profiles and multi-speaker support.
• Sentiment analysisDetects positive, neutral or negative sentiment at the sentence level.
• Key phrasesAutomatically extracts the most significant concepts and phrases from every transcript.
• Custom formattingNormalizes dates, phone numbers and email addresses into machine-readable formats.
• Auto chaptersBreaks long recordings into timestamped sections with an auto-generated summary for each chapter.
• Entity detectionIdentifies names, organizations, locations, dates and other entities across every transcript.
• Topic detectionClassifies audio content against the IAB standard taxonomy.

Sources

Pricing

Pricing page · 9 Oct 2026

Per audio hour, on top of the transcription rate: Speaker Identification $0.02 (low effort) or $0.10 (medium), Translation $0.06, Custom Formatting $0.03, Entity Detection $0.08, Sentiment Analysis $0.02, Key Phrases $0.01, Topic Detection $0.15, Summarization $0.02 (low effort) or $0.07 (medium). The changelog says the legacy summarization and auto_chapters parameters "will stop working on September 15, 2026". The one-time new-account credit covers these models and is not a recurring free tier.

Description

Official documentation · 9 Oct 2026

"AssemblyAI's Speech Understanding API is a single endpoint that turns audio into structured intelligence — speaker labels, sentiment, entities, topics, summaries, key phrases, translation, chapters, and custom formatting — in one request."

What it does

Pricing page · 9 Oct 2026

Summarization and Translation are two of the priced models; sentiment, entity and topic detection are the others.

Sold within

Official documentation · 9 Oct 2026

"Speech Understanding features are designed for pre-recorded audio. For real-time transcription, use AssemblyAI's Realtime Speech-to-Text API. You can pipe streaming transcripts into Speech Understanding post-call." Docs billing: "Add-on features (for example, Entity Detection or Medical Mode) are billed separately at their own hourly rates".

Name

Official documentation · 9 Oct 2026

Page heading: "Speech Understanding API".

URL

Official documentation · 9 Oct 2026

The product's own page.

Deployment

Official documentation · 9 Oct 2026

Hosted API.

Interfaces

Official documentation · 9 Oct 2026

"AssemblyAI maintains official SDKs for Python and JavaScript. Both SDKs cover pre-recorded transcription, real-time streaming, and speech understanding".

Modalities

Official documentation · 12 Oct 2026

Page: 'Extract structured insights from audio with Speech Understanding models. / extract meaningful information like speaker identities, sentiment, topics, and summaries'.

Intended for

Official documentation · 9 Oct 2026

An API for developers.

Also from AssemblyAI

• AssemblyAI Pre-recorded Speech-to-Text API API service

  Speech-to-text API for recorded audio and video files: transcripts in 99 languages with speaker diarization, language detection, word-level timestamps and keyterm prompting, billed per second of audio.

• AssemblyAI Realtime Speech-to-Text API API service

  Live transcription API: audio streamed over a WebSocket comes back as text within a few hundred milliseconds, with endpointing for voice agents, sold by the hour of session time and also offered self-hosted.

• AssemblyAI Voice Agent API API service

  One connection that runs a production voice agent end to end: speech recognition, a conversational language model, voice generation, turn detection, interruptions and tool calls, at one flat hourly rate.

• AssemblyAI LLM Gateway API service

  OpenAI-compatible API that routes requests to GPT, Claude, Gemini, Qwen and other hosted models with automatic fallbacks, at the providers' own token prices with no markup, beside AssemblyAI's speech APIs.

• AssemblyAI Guardrails API service

  Safety add-ons for transcription requests: profanity filtering, content moderation and redaction of personal data in the transcript text and in the audio itself, each toggled per request.

• Sync Speech-to-Text API API service

  Returns a transcript of a short audio clip in a synchronous API response.

• Dictation API API service

  Converts spoken audio into text with a cleanup pass and an accompanying verbatim transcript.

• Blurt Application

  Converts speech into text wherever the user is typing.

Open AssemblyAI in the directory

Something wrong here? Send a correction — quote this product id: assemblyai-speech-understanding.