Rev.ai

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.

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).

# 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)

// 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);

# 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'

Features

Links

• rev.ai ↗Product homepage — positioning, customers, and the developer-first pitch around the Reverb ASR model.
• rev.ai/pricing ↗Current per-hour and per-minute rates across Reverb, Reverb Turbo, Reverb FL, Whisper Fusion, human transcription, and the insights stack.
• docs.rev.ai ↗Documentation root — quickstarts, API reference, and feature guides for async, streaming, and the insights APIs.
• Async API reference ↗POST /speechtotext/v1/jobs reference — request body, transcriber options, diarization, custom vocab, callback URL.
• Streaming API reference ↗Real-time WebSocket endpoint — partial and final hypotheses, audio format requirements, session lifecycle.
• revdotcom/revai-python-sdk ↗Official Python SDK — async + streaming + insights, MIT licensed, actively maintained.
• revdotcom/revai-node-sdk ↗Official Node.js / TypeScript SDK — same feature surface as the Python SDK, MIT licensed.
• revdotcom/reverb ↗Open-source inference code for Rev's Reverb ASR and diarization models — Apache-2.0 code, models on HuggingFace, benchmarks vs Whisper Large-v3 and Canary-1B.
• Language identification docs ↗Pre-transcription language ID at $0.003/min — useful when the input language is unknown and you need to pick a transcriber.
• Summarization docs ↗Standard and premium summarization tiers running on a completed job id — pairs with topic extraction and sentiment.
• Rev blog ↗Product announcements, model releases (Reverb open-source 2024-10), and benchmarks.

Rev.ai vs Whipscribe

Alternatives to Rev.ai