Language code: en

English speech-to-text API

KolWrite transcribes English audio and video in one REST call and returns segments with word-level timestamps and speaker labels as JSON, plain text or SRT. For clear English recordings the Base model costs US$0.48 per audio hour; English is also the most common translation target for audio in the other 99 languages.

Get an API key Quickstart Supported languages

Last updated: · Markdown

Transcribe English with one request

Set language to en and start a job. Poll GET /transcribe/{jobId} for the result, or pass a webhook_url.

curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/meeting-en.m4a", "model": "oracle", "language": "en", "include_diarization": true, "output_format": "json"}'

Translate English audio into Spanish in the same job (Oracle models only):

curl https://app.kolwrite.com/transcribe \
  -H "x-api-key: $KOLWRITE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"audio_url": "https://example.com/meeting-en.m4a", "model": "oracle_mini", "language": "en", "translate_to": "es", "output_format": "srt"}'

English at a glance

PropertyDetails
API codeen
Native nameEnglish
Writing directionLeft to right
Automatic detectionYes: omit language or send "auto"
Translate English audio intoAny of the 100 supported languages, on Oracle models
Translate other languages into EnglishYes: translate_to: "en" on Oracle models
OutputJSON (segments, word timings, speakers), TXT, SRT
PriceUS$0.48 (Base) to US$3.60 (Oracle Max) per audio hour; US$1.44 on Oracle

What to know about English transcription

  • English accents differ widely (US, UK, Indian, Australian, African and many second-language accents). There is no accent setting; send language: "en" and test the accents your users have.
  • There is no US or UK spelling option. If your product needs one convention, apply it in post-processing.
  • For clean, single-speaker English such as dictation or narration, base is usually enough. Move to oracle for noisy meetings, phone audio or many speakers.
  • Any of the 100 languages can be translated into English with translate_to: "en" on an Oracle model, which makes English the hub for multilingual content.

Where teams use English transcription

  • Meeting notes and searchable archives with speaker labels.
  • Podcast and video captions (srt).
  • User-research interviews and sales calls.
  • Turning foreign-language recordings into English text with translate_to: "en".

Choosing a model

Start with oracle (US$1.44 per hour) for production English audio. Use base (US$0.48) for clean, single-speaker recordings at volume, oracle_mini (US$0.96) for the cheapest translation, and oracle_pro or oracle_max for noisy or difficult audio. KolWrite does not publish a English accuracy figure for this API, so test a sample of your own recordings before committing. Full comparison: models and prices.

Questions and answers

Which model should I use for English?

base for clear, single-speaker audio and high volume; oracle for production audio with noise, crosstalk or many speakers; oracle_max for the hardest recordings.

Can I get timestamps for every word?

Yes. JSON and SRT include word timings by default (word_timestamps: true) on models with word alignment. Plain Oracle Mini returns segment timestamps unless a speaker mode is on.

How much does an hour of English cost?

From US$0.48 on Base to US$3.60 on Oracle Max per audio hour, metered per second with no minimum.

Related pages