Tools

Audio Transcription API

Submit any audio file. Get back a full transcript with timestamps. MP3, WAV, M4A, and more.

Try it below:

FILEDrop a file or click to upload

Production-ready

Private by design

Security-first

Scalable

Production-ready

Private by design

Security-first

Scalable

Production-ready

Private by design

Security-first

Scalable

Transcribe audio files

Upload an audio file or submit a URL, get a transcript back.

{
  "items": [
    {
      "sequence": 1,
      "timeStart": 0.0,
      "timeEnd": 8.2,
      "text": "Hi, thanks for calling Acme support. My name is James. How can I help you today?"
    },
    {
      "sequence": 2,
      "timeStart": 8.2,
      "timeEnd": 18.6,
      "text": "Hi James, I'm having trouble with the webhook configuration. I set the URL in the dashboard but I'm not receiving any notifications when jobs complete."
    },
    {
      "sequence": 3,
      "timeStart": 18.6,
      "timeEnd": 31.4,
      "text": "OK, let me pull up your account. Can you confirm which endpoint you configured? And are you seeing any entries in the webhook logs?"
    },
    {
      "sequence": 4,
      "timeStart": 31.4,
      "timeEnd": 45.1,
      "text": "The endpoint is our staging server, https://staging.example.com/webhooks. I checked the logs and there's nothing there at all. No attempts."
    }
  ],
  "total": 12,
  "start": 1,
  "end": 4
}

Start for free

Read the docs

What is Exabase's audio transcription API?

Submit an audio file to the Exabase Extract API and get a transcript back. The response includes the full transcript text and the transcript split into timestamped chunks. Each chunk carries timeStart and timeEnd in seconds, so you can map any piece of text back to the exact moment in the recording. MP3, WAV, M4A, OGG, FLAC, and other major formats are supported.

The same POST /v2/extract endpoint accepts both file uploads and URLs pointing to hosted audio. Transcription runs on Exabase's infrastructure. No speech-to-text model to deploy, no GPU to provision, no Whisper to manage.

What you get back

The response includes the full transcript in extraction.media.transcript and the transcript split into chunks. Each chunk carries a timeStart, timeEnd, and the transcript text for that segment. You also get the audio duration, MIME type, file size, total chunk count, and a CDN-hosted thumbnail. The API reference has the complete response schema.

One multi-modal API

The same POST /v2/extract endpoint handles every content type Exabase supports. For audio, it transcribes and returns timestamped chunks. For video, it does the same with the addition of frame dimensions. For PDFs, it returns text chunks with page numbers and (for recognised document types) structured field extraction. For images, it runs OCR. For web pages, it renders JavaScript and extracts the content.

The submission flow is identical across all types: one endpoint, one SDK method, one webhook configuration. You learn the pattern once and use it for everything. The Extract docs cover each content type in detail.

What you can build with it

Transcribe podcast episodes and make every word searchable. Process customer support calls and search across all conversations for specific topics. Index meeting recordings so your team can find what was said and when. Build a voice memo app where spoken notes become searchable text.

Store transcribed audio as Resources in a Base and the transcript becomes searchable through Deep Search at the chunk level. Feed timestamped chunks into a RAG pipeline so your agent can cite the exact moment in a recording. Workers can process new recordings as they arrive, keeping your transcript index current without manual work.

Beyond transcription

The Extract API returns more than a transcript. You get audio duration, MIME type, file size, a CDN-hosted thumbnail, and searchable chunks. Store the output as a Resource and it's searchable through Deep Search immediately. Extract key details into Memory so your agent retains what it heard between sessions. The Submitting Jobs guide at https://exabase.io/docs/developer-guide/extraction/submitting-jobs walks through the full flow.

Start for free

Read the docs

How do I use it?

  1. Get your API key

Free, no credit card:

Sign up at exabase.io and copy your API key from the dashboard.

  1. Submit an audio file

Using the SDK (Node.js):

import { Exabase } from "@exabase/sdk";
import { createReadStream } from "fs";

const api = new Exabase({
  apiKey: process.env.EXABASE_API_KEY,
});

const job = await api.extract.createFromFile({
  file: createReadStream("./support-call.mp3"),
  name: "Support call — ticket #4821",
});

console.log(job.id);    // extraction job id
console.log(job.state); // "pending"

  1. Get the transcript

Poll the job until state reaches completed, or skip polling entirely with webhooks.

const result = await api.extract.get({ jobId: job.id });

if (result.state === "completed") {
  console.log(result.extraction?.media?.transcript); // full transcript
  console.log(result.extraction?.media?.duration);   // duration in seconds

  const chunks = await api.extract.getChunks({
    jobId: job.id,
    start: 1,
    end: 20,
  });

  for (const chunk of chunks.items) {
    console.log(chunk.timeStart, chunk.timeEnd, chunk.text);
  }
}

One API call. No speech-to-text model, no GPU, no Whisper.

What you get back

Extraction job

Field

Type

Description

state

string

completed or failed

kind

string

audio

extraction.common.mimeType

string

Detected MIME type (e.g. audio/mpeg)

extraction.common.size

number

File size in bytes

extraction.common.thumbnail

string

CDN-hosted thumbnail URL

extraction.common.chunkCount

number

Number of transcript chunks

extraction.media.duration

string

Duration in seconds

extraction.media.transcript

string

Full transcript text

Transcript chunks

Field

Type

Description

sequence

number

Chunk position in the transcript

text

string

Transcript text for this segment

timeStart

number

Start time in seconds

timeEnd

number

End time in seconds

Chunks are paginated. Pass start and end to GET /v2/extract/{jobId}/chunks to page through them.

API quick reference

Endpoint

Method

Description

/v2/extract

POST

Submit extraction job

/v2/extract

GET

List extraction jobs

/v2/extract/{jobId}

GET

Poll for result

/v2/extract/{jobId}/chunks

GET

Fetch transcript chunks

/v2/extract-settings

PUT

Configure webhook

Auth: X-Api-Key header on all requests.

File retention: Stored files are retained for 1 day from job creation. Download or copy anything you need before they expire.

Need file extraction or full page content?

Exabase offers a full set of tools to extract content from any media, document or website.

All your data extraction needs in one place.

Learn about Exabase Extract →

Why Exabase

Timestamps on every chunk

The transcript is split into chunks, each with a start and end time in seconds. Build seek-to-source UIs, generate subtitles, or link citations directly to the right moment in the recording.

Timestamps on every chunk

The transcript is split into chunks, each with a start and end time in seconds. Build seek-to-source UIs, generate subtitles, or link citations directly to the right moment in the recording.

Text as searchable chunks

Extracted text is split into structured chunks with page numbers. Build search, feed chunks into RAG pipelines, or index them directly. Not a single giant text blob.

Text as searchable chunks

Extracted text is split into structured chunks with page numbers. Build search, feed chunks into RAG pipelines, or index them directly. Not a single giant text blob.

No model hosting

Transcription runs on Exabase's infrastructure. No Whisper deployment, no GPU provisioning, no model version management. Submit a file, get a transcript back.

No model hosting

Transcription runs on Exabase's infrastructure. No Whisper deployment, no GPU provisioning, no model version management. Submit a file, get a transcript back.

Async processing that scales

Submit hundreds of recordings and let the pipeline handle them. Poll for results or set up webhooks and process completions as they arrive. No timeouts, no recording-length limits.

Async processing that scales

Submit hundreds of recordings and let the pipeline handle them. Poll for results or set up webhooks and process completions as they arrive. No timeouts, no recording-length limits.

One API for everything

The same POST /v2/extract endpoint handles audio, video, PDFs, images, and web pages. The response structure adapts to the content type. Learn one API, extract from anything.

One API for everything

The same POST /v2/extract endpoint handles audio, video, PDFs, images, and web pages. The response structure adapts to the content type. Learn one API, extract from anything.

Webhooks with delivery logs

No need to poll. Configure a webhook URL and get notified on completion. Every delivery attempt is logged with status codes and response bodies. You can manually re-trigger a webhook if your server missed it.

Webhooks with delivery logs

No need to poll. Configure a webhook URL and get notified on completion. Every delivery attempt is logged with status codes and response bodies. You can manually re-trigger a webhook if your server missed it.

Reprocess without re-uploading

If a job fails, call the reprocess endpoint. The API retries using the original file without requiring a new upload.

Reprocess without re-uploading

If a job fails, call the reprocess endpoint. The API retries using the original file without requiring a new upload.

Same account for full platform access

Transcription is one capability. The same Exabase account gives you Memory, Deep Search, Resources, and Workers. Same API key, different endpoints.

Same account for full platform access

Transcription is one capability. The same Exabase account gives you Memory, Deep Search, Resources, and Workers. Same API key, different endpoints.

Comparisons

vs Deepgram

Deepgram is a fast, accurate speech-to-text platform with features like diarisation, language detection, and real-time streaming. If you need those capabilities, Deepgram is purpose-built for them. Exabase returns transcripts as indexed chunks that feed directly into the rest of the platform: store them as Resources, search them with Deep Search, keep them current with Workers. Transcription as part of a complete data layer, not a standalone service.

vs Deepgram

Deepgram is a fast, accurate speech-to-text platform with features like diarisation, language detection, and real-time streaming. If you need those capabilities, Deepgram is purpose-built for them. Exabase returns transcripts as indexed chunks that feed directly into the rest of the platform: store them as Resources, search them with Deep Search, keep them current with Workers. Transcription as part of a complete data layer, not a standalone service.

vs AssemblyAI

AssemblyAI offers audio intelligence features beyond transcription: sentiment analysis, topic detection, entity recognition, and content moderation. If you need that level of audio analysis, use AssemblyAI. If you need transcription with timestamps as part of a broader platform (storage, search, memory, automation), Exabase handles the transcription and gives you the infrastructure alongside it.

vs OpenAI Whisper API

The Whisper API is synchronous and returns a plain transcript. For short clips that's fine. For longer recordings, you manage chunking, retries, and rate limits yourself. Exabase processes asynchronously with no file-length constraints, returns timestamped chunks, and gives you webhooks so you don't have to poll. The transcript feeds directly into the rest of the platform if you need it.

Works with other Exabase features

Memory

Self-managing advanced memory system.

Bases

Isolated per-tenant instances with version rollback.

Resources

Files, notes, links. Your portable context server.

Deep Search

Sub-document multi-modal hybrid search.

Extract

Structured data from PDFs, websites, images, and more.

Workers

Autonomous agents and self-enriching knowledge bases.

Memory

Self-managing advanced memory system.

Bases

Isolated per-tenant instances with version rollback.

Resources

Files, notes, links. Your portable context server.

Deep Search

Sub-document multi-modal hybrid search.

Extract

Structured data from PDFs, websites, images, and more.

Workers

Autonomous agents and self-enriching knowledge bases.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Ready for scale

Fast

Deliver speed to your users. Infrastructure that won't slow your agent down.

Secure

Encrypted in transit (SSL) and at rest (AES-256). CASA certified.

Reliable

99.9% uptime. Built on Exabase's consumer-grade scaled infrastructure.

Use cases

Podcast search

Transcribe episodes and make every word searchable. Listeners find the right episode and the exact moment, not just the show page.

Call centre analytics

Transcribe customer support calls. Search across all conversations for specific topics, complaints, or resolutions. Each chunk maps to a timestamp for review.

Call centre analytics

Transcribe customer support calls. Search across all conversations for specific topics, complaints, or resolutions. Each chunk maps to a timestamp for review.

Meeting recording search

Transcribe team meetings and index them. Search across all meetings by topic, decision, or action item. Deep Search returns the exact moment in the recording.

Meeting recording search

Transcribe team meetings and index them. Search across all meetings by topic, decision, or action item. Deep Search returns the exact moment in the recording.

Voice memo apps

Let users record voice notes and search them as text. Transcripts are stored and indexed automatically. Spoken notes become as searchable as typed ones.

RAG with audio sources

Feed transcript chunks into your retrieval-augmented generation pipeline. Your agent answers questions about what was said and cites the timestamp.

RAG with audio sources

Feed transcript chunks into your retrieval-augmented generation pipeline. Your agent answers questions about what was said and cites the timestamp.

Content repurposing

Transcribe interviews, lectures, and panel discussions. Use the timestamped chunks as source material for articles, summaries, or social posts.

Accessibility and compliance

Generate transcripts for audio content to meet accessibility requirements. Timestamped chunks provide the raw material for captions or text alternatives.

Accessibility and compliance

Generate transcripts for audio content to meet accessibility requirements. Timestamped chunks provide the raw material for captions or text alternatives.

Subtitle generation

Use the timestamped transcript chunks as a starting point for subtitle files. Each chunk maps to a time range in the recording.

Language learning platforms

Transcribe audio lessons with timestamps. Students search for specific words or phrases and jump to the exact moment in the recording.

FAQs

What is Exabase?

Exabase is infrastructure for AI agents. It gives your agents memory, versioned file storage, AI deep search, and context automation through a set of APIs. Store what your agent learns, search inside any content type, and keep knowledge bases current automatically. Built for production use. Give your agent precise context and cut your token spend by up to 81%.

Who uses Exabase?

Developers and teams building AI agents, copilots, and RAG applications. If your agent needs to remember things between sessions, store and retrieve files, search across documents and media, or stay up to date without manual maintenance, Exabase handles that infrastructure so you can focus on your product.

How fast is transcription?

Processing time depends on the file length and format. Processing is asynchronous, so your application is not blocked while transcription runs. Poll for results or configure a webhook to be notified on completion.

What audio formats are supported?

MP3, WAV, M4A, OGG, FLAC, and other major audio formats. The API auto-detects the content type and processes accordingly.

Does it support speaker diarisation?

The API returns a full transcript split into timestamped chunks. Speaker diarisation (identifying who said what) is not currently a separate output field.

What do transcript chunks look like?

Each chunk contains the transcript text, a sequence number, and timeStart / timeEnd values in seconds. You can map any piece of text back to the exact moment in the recording.

Can I submit a URL instead of uploading a file?

Yes. Pass a url field in the request body pointing to a publicly accessible audio file. Exabase fetches and processes it.

Do I have to poll for results?

No. You can configure a webhook URL and Exabase will POST the full result to your server when processing completes. The webhooks guide covers setup.

Is there a file length limit?

Processing is asynchronous with no hard recording-length limit. Long files take proportionally longer to process.

What happens if transcription fails?

The job state moves to failed. You can call the reprocess endpoint to retry without re-uploading the original file.

How long are files retained?

Stored files are retained for 1 day from job creation, then permanently deleted. Download or copy anything you need before the retention window expires.

How is this different from the Audio to JSON tool?

The Audio to JSON page covers the full extraction response: metadata, duration, thumbnail, transcript, and chunks. Audio Transcription focuses specifically on the transcript and timestamped chunks. Same underlying API, different emphasis.

Can I use the transcript with other Exabase features?

Yes. Store transcribed audio as a Resource in a Base and the transcript becomes searchable through Deep Search. Extract key details into Memory so your agent retains what it heard. Workers can process new recordings on a schedule.

Is there an SDK?

Yes. The @exabase/sdk package for Node.js/TypeScript handles file streaming, job polling, and chunk retrieval. Install with npm install @exabase/sdk. Or call the REST API directly from any language.

What other content types does Extract support?

PDFs, images (with OCR), video files (with transcription), web pages, and documents. The same POST /v2/extract endpoint handles all of them. See the PDF to JSON, Image to Text, Video Transcription, and Website to JSON tool pages.

Other tools

Token cost calculator

Link preview API

PDF thumbnail generator

PDF to JSON

Website to JSON

Audio to JSON

Video to JSON

Image to JSON

Invoice to JSON

Contract to JSON

Resume to JSON

PDF to chunks

Image to text

Audio transcription

Video transcription

Token cost calculator

Link preview API

PDF thumbnail generator

PDF to JSON

Website to JSON

Audio to JSON

Video to JSON

Image to JSON

Invoice to JSON

Contract to JSON

Resume to JSON

PDF to chunks

Image to text

Audio transcription

Video transcription

Deciding?

Ask your favourite AI about Exabase:

Cut your token spend and give your agent precise context.

Get started in minutes.

Start for free

Read the docs

Cut your token spend and give your agent precise context.

Get started in minutes.

Start for free

Read the docs