Audio2Text API

Add AI transcription to your product in minutes. Upload audio or video, receive JSON with timecodes, speakers, and confidence scores. Webhooks available.

$0.06 per minute — simple usage-based pricing
⏱️
Timestamps & confidence

Word-level timestamps and confidence scores in JSON.

🗣️
Speaker diarization

Accurate multi-speaker labeling for meetings and interviews.

🔉
Noise & filler cleanup

Automatic noise reduction and filler removal for cleaner text.

🔔
Webhooks & polling

Notifications when jobs are ready or on-demand status checks.

$0.06/min
Threshold or monthly billing. No commitments, cancel anytime.

Billing options

  • Threshold billing: we authorize a small amount, then auto-charge as your usage passes dynamic thresholds. Thresholds increase as account history builds.
  • Monthly billing: one invoice at the end of the month for minutes consumed (Google Ads style).

Included features

  • Multi-language speech-to-text with timestamps
  • Speaker diarization (multi-speaker labeling)
  • Noise reduction and filler cleanup
  • Exports: TXT, SRT, VTT, DOCX

Quick start

curl -X POST \
  https://audio2text.click/api/v1/transcriptions \
  -H "Authorization: Bearer <API_KEY>" \
  -F file=@sample.mp3 \
  -F language=en \
  -F diarization=true

# Polling
curl https://audio2text.click/api/v1/transcriptions/job_123 \
  -H "Authorization: Bearer <API_KEY>"

Limits & quotas

  • Default rate limit: 60 requests/min per key (burstable).
  • Max file size: 500 MB via direct upload; contact us for larger files.
  • Concurrent jobs: up to 5 per account by default.

SDKs & libraries

  • Node.js SDK (beta) — coming soon
  • Python SDK (beta) — coming soon
  • OpenAPI spec — available on request

Security & data handling

  • Data encrypted in transit (TLS) and at rest.
  • Temporary storage only for processing; opt-in retention for QA.
  • Role-based access on dashboard; API keys scoped and revocable.
Thanks! We’ll reach out with keys and docs shortly.