Rev.ai

by Rev.ai

Rev.ai is Rev's developer API arm — Reverb ASR plus real-time streaming, with the unique option to drop the same job down to human transcribers when machine-grade accuracy isn't enough.

Looking at Rev.ai? Try this first.

Drop your audio. Transcript in seconds. First transcript free, then $2 a file or $8 = 1,000 min

TL;DR

Rev.ai exposes async transcription via POST /speechtotext/v1/jobs and real-time via a WebSocket streaming endpoint, both powered by the Reverb model family — Rev's in-house English ASR that was open-sourced in October 2024 (Apache-2.0 code, models on HuggingFace) and benchmarks competitively against Whisper Large-v3. Word-level timestamps, diarization, custom vocabulary, language identification, sentiment, topic extraction, and summarization are all wired into the same job submission.

Best for long-form English media, podcasts, and call recordings where accuracy matters more than headline price, plus any workflow that occasionally needs to escalate the same audio to human transcribers under one vendor. Current pricing: Reverb at $0.20/hr (~$0.0033/min), Reverb Turbo at $0.10/hr (~$0.0017/min), Reverb foreign language at $0.30/hr, Whisper Fusion / Whisper Large at $0.005/min, and human transcription at $1.99/min. New accounts get free credit equivalent to 5 hours of Reverb ASR.

What it is

Rev.ai is the developer API from Rev, historically a human-transcription service. The "Machine" endpoint is competitive on English and supports custom vocabulary that handles jargon better than generic Whisper. HIPAA-eligible on appropriate plans. Last price check: 2026-04-20.

Best for: English-heavy workloads where vocabulary customization matters (medical, legal, technical).
Watch out for: Pricier than Whisper-based APIs; non-English coverage narrower.

Install / use

POST https://api.rev.ai/speechtotext/v1/jobs

View Rev.ai API docs ↗

Where Rev.ai fits · 6 use-cases

Rev.ai's pitch clusters around English ASR accuracy, the Reverb open model, and the optional human-grade escalation lane. Pick the card closest to your build — each links to the matching docs.rev.ai section.

Podcasts · long-form English

Async · Reverb model

Submit an episode URL to the async jobs endpoint and ask for diarization plus word timestamps. Reverb is tuned on Rev's 7M+ hours of human-verified speech, which shows up on long-form conversational English versus generic Whisper.

POST /speechtotext/v1/jobs
transcriber=reverb · diarize=true

Media · subtitles + chapters

Async · forced alignment

Use forced alignment to lock an existing transcript to word-level timestamps for SRT/VTT export, or run a fresh job with diarization for caption tracks plus speaker labels. Topic extraction can seed chapter markers.

Forced alignment endpoint
Word-accurate timing for caption files

Voice agents · streaming

WebSocket · real-time

Open a WebSocket to the streaming endpoint and pipe PCM frames; partial hypotheses arrive in real time for live captioning, IVR turn-taking, and in-product voice copilots. Custom vocabulary biases brand and jargon words.

Streaming Speech-to-Text
Real-time partials + final results

LLM pre-processing

Async + Insights stack

Bundle the transcript with summarization, topic extraction, and sentiment in a single workflow so the LLM downstream sees structured input instead of raw text. Useful for meeting bots, RAG over call audio, and analytics rollups.

Summary + Topics + Sentiment APIs
Insights stack runs on the same job id

Compliance · legal records

Human option · HIPAA / SOC II

When machine accuracy is not enough, Rev.ai can route the same job to its human transcription network for verbatim, certified output. Same API, same dashboard, same audit trail — useful for depositions, regulatory filings, and accessibility compliance.

Human transcription job type
$1.99/min · turnaround in hours

Multilingual fallback

Reverb FL + Whisper Fusion

For non-English audio, Rev.ai exposes a Reverb Foreign Language model plus Whisper Fusion / Whisper Large as transcriber options, with language identification as a pre-step when the input language is unknown. 57+ languages on the broader stack.

transcriber=reverb-fl | whisper-fusion
Language ID at $0.003/min seeds the choice

Pattern: Rev.ai is the right call when English accuracy and the option to escalate to humans under one vendor matter more than the lowest per-minute rate. If you want lower streaming latency, Deepgram is the closest comparison; if you want to skip the integration step entirely, drop a URL into Whipscribe below.

Quickstart · pick a runtime

Three working ways to submit a pre-recorded URL to the async jobs endpoint. Export your access token as REV_AI_API_KEY first — grab one from your Rev.ai dashboard (free credit equivalent to 5 hours of Reverb ASR on new accounts).

1Python SDK · async URL

Official rev_ai SDK · submit a URL job and poll for the transcript.

# pip install rev_ai
import os, time
from rev_ai import apiclient

client = apiclient.RevAiAPIClient(os.environ["REV_AI_API_KEY"])

job = client.submit_job_url(
    "https://www.rev.ai/FTC_Sample_1.mp3",
    metadata="podcast-001",
    transcriber="reverb",
)

while True:
    details = client.get_job_details(job.id)
    if details.status.name in ("TRANSCRIBED", "FAILED"):
        break
    time.sleep(5)

transcript = client.get_transcript_text(job.id)
print(transcript)

Source: revdotcom/revai-python-sdk ↗ · full options at docs.rev.ai/api/asynchronous ↗

2Node / JavaScript SDK

Official revai-node-sdk · same async URL job from Node 18+.

// npm install revai-node-sdk
import { RevAiApiClient } from "revai-node-sdk";

const client = new RevAiApiClient(process.env.REV_AI_API_KEY);

const job = await client.submitJobUrl(
  "https://www.rev.ai/FTC_Sample_1.mp3",
  { metadata: "podcast-001", transcriber: "reverb" }
);

let details;
do {
  await new Promise(r => setTimeout(r, 5000));
  details = await client.getJobDetails(job.id);
} while (details.status === "in_progress");

const transcript = await client.getTranscriptText(job.id);
console.log(transcript);

Source: revdotcom/revai-node-sdk ↗

3cURL · no SDK

Plain HTTPS POST to /speechtotext/v1/jobs · useful for shell pipelines and edge runtimes.

# submit a URL job
curl --request POST \
  --url 'https://api.rev.ai/speechtotext/v1/jobs' \
  --header "Authorization: Bearer $REV_AI_API_KEY" \
  --header 'Content-Type: application/json' \
  --data '{
    "source_config": {"url": "https://www.rev.ai/FTC_Sample_1.mp3"},
    "metadata": "podcast-001",
    "transcriber": "reverb"
  }'

# poll job status
curl --request GET \
  --url "https://api.rev.ai/speechtotext/v1/jobs/<JOB_ID>" \
  --header "Authorization: Bearer $REV_AI_API_KEY"

# fetch the transcript when status=transcribed
curl --request GET \
  --url "https://api.rev.ai/speechtotext/v1/jobs/<JOB_ID>/transcript" \
  --header "Authorization: Bearer $REV_AI_API_KEY" \
  --header 'Accept: text/plain'

Source: docs.rev.ai/api/asynchronous ↗

What people actually do with Rev.ai-style transcription

The tool is the means. These are the jobs — each one priced at published rates, each one wired up on its own page.

Transcribe a whole back catalogue in one runThe archive is the asset, but one-at-a-time upload means it never gets done.…1,000 hours ≈ $480, onceTranscribe every new file in a Drive folderFiles accumulate in a folder nobody opens, and the knowledge in them is invisible to search.…≈ $0.48 per audio hourCut short-form clips out of a webinar automaticallyThe clips worth posting are buried somewhere in a 60-minute recording and finding them by scrubbing costs more than the…60-min webinar ≈ $0.48

Wire it into Amazon S3 n8n Make.com Google Drive Zapier Slack

Features

Speaker diarization	Yes
Word-level timestamps	Yes
Streaming / real-time	Yes
Languages supported	36
HIPAA eligible	Yes

Rev.ai vs Whipscribe

Feature	Rev.ai	Whipscribe
Category	Transcription APIs	Transcription APIs
Pricing	Not verified	$8–$24 one-time packs (credits never expire) · $2 single unlock · free instant preview
Speaker diarization	Not verified	Yes
Word timestamps	Not verified	Yes
Streaming	Not verified	No
Languages	36	99
Platforms	API	Web, API, MCP

Where this category is heading

From the vendor changelogs we track weekly — what changed in August 2026, and what it means if you are choosing now.

Insight on top of the transcript, not sold separately

AssemblyAI moved summarisation onto an LLM this month; every vendor is racing to return action items, quotes and topics with the text rather than as an add-on.

Whipscribe today Every Whipscribe job already returns an insights payload — summary, key quotes, topics and speakers — from the same job id, at no extra charge.

Private, secured deployment

Deepgram shipped self-hosted container images in August — the market is moving toward audio that stays inside a boundary the customer controls, because teams with customer calls or unreleased material are refusing shared model endpoints.

Whipscribe today Whipscribe runs on our own GPUs in a private, secured cloud. Audio is never forwarded to OpenAI or any third-party model.

Agents calling transcription as a tool

The fastest-growing way to use a transcription API is not a form — it is Claude, Cursor or a workflow runner calling it mid-task through MCP.

Whipscribe today Whipscribe ships an MCP server: transcribe, search and summarise from an assistant without wiring anything.

Async and batch over one-file-at-a-time

AssemblyAI's 1.0 SDK unified async, realtime and sync; Deepgram's CLI went to 0.3. The unit of work is becoming the folder or the bucket, not the file.

Whipscribe today Submit with an Idempotency-Key and a batch_id, poll by job, retry safely. The S3 connector runs a whole prefix in one grant.

More languages, unevenly

Deepgram added Afrikaans, Georgian and Armenian and improved a dozen more this month. Coverage is widening while quality still clusters around English and the large European languages.

Whipscribe today 99+ languages auto-detected. Ask for a language explicitly when you know it — auto-detect on a short or noisy clip is the most common cause of a wrong-language transcript.

Source: Deepgram and AssemblyAI changelogs, scanned 2026-08-24.

Alternatives to Rev.ai

OpenAI Whisper API

OpenAI

Hosted Whisper large-v3 from OpenAI — $0.006 per minute.

$0.006/min

AssemblyAI

Universal-2 model + diarization, PII redaction, topic detection, summarization.

from $0.37/hr

Deepgram

Nova-2 model, excellent streaming, strong at conversational audio.

from $0.0043/min

Frequently asked about Rev.ai

What is Rev.ai?

Rev.ai exposes async transcription via POST /speechtotext/v1/jobs and real-time via a WebSocket streaming endpoint, both powered by the Reverb model family — Rev's in-house English ASR that was open-sourced in October 2024 (Apache-2.0 code, models on HuggingFace) and benchmarks competitively against Whisper Large-v3. Word-level timestamps, diarization, custom vocabulary, language identification, sentiment, topic extraction, and summarization are all wired into the same job submission.

How much does Rev.ai cost?

Rev.ai is a paid product — published pricing: from $0.02/min. Pricing changes; verify on the vendor's own page before budgeting.

What platforms does Rev.ai support?

Rev.ai is an API — you call it from whatever you build, on any platform with an HTTP client.

How do I get started with Rev.ai?

Rev.ai is used through its API: get a key from the vendor, then call it from your own code. There is no desktop app to install.

How many languages does Rev.ai support?

Rev.ai lists 36 languages.

What are the limitations of Rev.ai?

Pricier than Whisper-based APIs; non-English coverage narrower.

Who is Rev.ai best for?

English-heavy workloads where vocabulary customization matters (medical, legal, technical).

What should I know before choosing Rev.ai?

Best for long-form English media, podcasts, and call recordings where accuracy matters more than headline price, plus any workflow that occasionally needs to escalate the same audio to human transcribers under one vendor. Current pricing: Reverb at $0.20/hr (~$0.0033/min), Reverb Turbo at $0.10/hr (~$0.0017/min), Reverb foreign language at $0.30/hr, Whisper Fusion / Whisper Large at $0.005/min, and human transcription at $1.99/min. New accounts get free credit equivalent to 5 hours of Reverb ASR.

Is Rev.ai open source?

No. Rev.ai is a proprietary API. If you need source you can read and run yourself, the open-source tools in this directory are the place to look.

What kind of tool is Rev.ai?

In this directory Rev.ai is filed under commercial api as a API.

What are the alternatives to Rev.ai?

There is a side-by-side page at /tools/rev-ai-alternatives comparing Rev.ai with the closest tools in the same category on price, platform and features.

Are there setup recipes for Rev.ai?

Yes — this page carries 3 tested setups: Python SDK · async URL; Node / JavaScript SDK; cURL · no SDK.

Can I automate Rev.ai-style transcription without running it myself?

Yes. If what you want is transcripts rather than the tool itself, Whipscribe does the same job as a hosted API: submit a file or URL, poll a job id, pull the result as txt, json, srt, vtt or docx. $0.008 a minute — about $0.48 an audio hour — bought as credits that never expire. The automation recipes on this site show it wired to Drive folders, Zoom recordings, S3 buckets and no-code platforms.

How is Whipscribe different from Rev.ai?

Rev.ai is another vendor's product; Whipscribe is a per-minute transcription service. We run the models on our own GPUs in a private cloud — audio is never forwarded to OpenAI or any third-party model — and every job returns five formats plus an AI summary, quotes and topics. Your first transcript in the web app is free at any length, no card.

What does transcription cost if I use Whipscribe instead of Rev.ai?

$0.008 a minute — about $0.48 an audio hour — bought as credits that never expire. There is no subscription and no monthly minimum: a 3-hour recording is about $1.44, a thousand-hour archive is about $480 once. Your first transcript in the web app is free at any length, no card, so you can check accuracy on your own audio before paying anything.

Whipscribe is a managed faster-whisper + whisperX service. If you want transcripts without running infrastructure, paste a URL or drop a file in the form below — you'll have a transcript in seconds.

Explore

All transcription tools · Audio technology hub · Transcribe any platform · Audio & video formats · How-to guides · Glossary · Playbooks · Apps · Broadcast & radio · Podcast transcripts · Use cases · Blog · Transcription API · Integrations · Automations · For your industry