Zoom AI Services: Speech Summarization API
Zoom AI Services: Speech Summarization API

Turn speech into
summaries built for
your workflow

Go from audio to a structured summary in one API call. Speech Summarization API (Fast) combines transcription and summarization to deliver key information within seconds. Add Custom Templates to shape the output and Language Understanding to keep the wording neutral and focused on facts.

Try demo See pricing
Speech Summarization
Capabilities
Capabilities

One API, tailored to the job

Speech Summarization API (Fast)

Speech Summarization
API (Fast)

Send speech audio and receive a structured summary and insights in one call. Transcription and summarization work together to produce results within seconds.

Language Understanding - Add-on

Language Understanding ·
Add-on

Filter sentiment and subjective language from transcripts to produce neutral summaries focused on factual content and key information. Available only with Speech Summarization API.

Custom Templates - Add-on*

Custom Templates ·
Add-on*

Define output sections, structure, and formatting rules so summaries align with a business workflow, reporting standard, or organizational requirement.

*Coming soon.

See how the summaries measure up

See how the summaries measure up

Summaries cover more than 90% of consequential discussion points with accurate capture of key facts — so the information that matters most is never left out.

Performance
Performance

Leading quality at the lowest
entry price

Up to 2.6x lower cost per meeting than leading alternatives

Up to 2.6x lower cost per meeting than leading alternatives

Zoom Speech Summarization delivers the lowest combined cost per meeting on average, compared with several tested configurations, by combining ASR (speech-to-text transcription) and LLM (summarization) costs into a single blended rate.

Strong summary quality at a competitive total cost

Strong summary quality at a competitive total cost

Zoom Speech Summarization sits in the upper-left corner — the best value position — delivering a strong average quality score at the lowest cost per meeting among all tested configurations.

One foundation
One foundation

Make spoken information useful wherever
work happens

Start with speech summarization, then shape the result for the people and systems that use it.

  1. Customer conversations

    Customer conversations

    Create concise call summaries for follow-up and review. Use a custom template to fit the fields your team already records.
  2. Meetings and interviews

    Meetings and interviews

    Capture the main information from a discussion without writing a recap from scratch. Format the summary for its intended audience.
  3. Reporting workflows

    Reporting workflows

    Apply consistent sections across summaries. Add Language Understanding when reports need neutral wording centered on factual content.
Try it
Try it

Hear the conversation. See the summary.

Generate summaries and next steps directly from the audio of meetings, phone calls, and other conversations.

Sign-up or login is required to access the portal.

Try the playground
Developer first
Developer first

Start summarizing in minutes

  • Simple, well-documented APIs
  • REST API and OpenAPI spec
  • Comprehensive error handling
  • Flexible summary length controls
See API docs
Pricing
Pricing

Simple, transparent pricing

Apply prepaid credits to your use of Speech Summarization API with transparent rates.

Speech Summarization API (Fast)

23¢

  • /hour
  • Speech Summarization API Fast turns speech audio directly to structured summaries and insights within seconds by combining speech-to-text transcription with text summarization in a single API call.
  • Usage is measured based on the total duration of audio submitted for summarization in minutes during a given billing period.

Language Understanding Add-on

5¢

  • /hour
  • Language Understanding API filters out sentiment and subjective language from transcripts, delivering neutral, objective summaries focused on factual content and key information.
  • Available as an add-on with Speech Summarization API only.
  • Usage is measured based on the total duration of audio submitted for language understanding analysis in minutes during a given billing period.

Ready to build with a leading speech understanding API?

Get started
See pricing