Spiral gives your agent every tool with one account. Browse the tools →

DeepgramAudioAvailable now

Whisper Large Speech to Text

whisper-large

Transcribe audio and video to text with Whisper Large Speech to Text from Deepgram through one Spiral API key. Transcribes recorded audio in 100+ languages with OpenAI Whisper Large hosted by Deepgram. Returns a JSON transcript. Slower than Nova models and limited to about 20 minutes of processing per file. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

Pricing

$0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute.

Limits

Runs
In the background
Returns
json
Longest queue wait
1 hour
Run deadline
30 minutes
Longest run, end to end
930 minutes
Largest inline input
1 MB
Largest input file
2 GB
Largest output
5 GB

Input

FieldKindDefaultDescription
url requiredURL or file—

Audio file URL to transcribe

extraJSON—

Arbitrary key-value pairs that are attached to the API response for usage in downstream processing

redactJSONfalse

Redaction removes sensitive information from your transcripts

searchJSON—

Search for terms or phrases in submitted audio

diarizetrue or falsefalse

Deprecated: use diarize_model instead. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0.

replaceJSON—

Search for terms or phrases in submitted audio and replaces them

encodingone of
linear16, flac, mulaw, amr-nb, amr-wb, opus, speex, g729
—

Specify the expected encoding of your submitted audio

keywordsJSON—

Keywords can boost or suppress specialized terminology and brands. keywords is not supported with Nova-3 models; use keyterm instead.

languageone of
af, am, ar, as, az, ba, be, bg, bn, bo, br, bs, ca, cs, cy, da, de, el, en, en-AU, en-GB, en-IN, en-NZ, en-US, es, es-419, es-LATAM, et, eu, fa, fi, fo, fr, fr-CA, gl, gu, ha, haw, he, hi, hi-Latn, hr, ht, hu, hy, id, id-ID, is, it, ja, jw, ka, kk, km, kn, ko, la, lb, ln, lo, lt, lv, mg, mi, mk, ml, mn, mr, ms, mt, my, ne, nl, nn, no, oc, pa, pl, ps, pt, pt-BR, pt-PT, ro, ru, sa, sd, si, sk, sl, sn, so, sq, sr, su, sv, sw, ta, te, tg, th, tk, tl, tr, tt, uk, ur, uz, vi, yi, yo, zh, zh-CN, zh-TW
en

The BCP-47 language tag that hints at the primary spoken language.

numeralstrue or falsefalse

Numerals converts numbers from written format to numerical format

dictationtrue or falsefalse

Dictation mode for controlling formatting with dictated speech

punctuatetrue or false—

Add punctuation and capitalization to the transcript Left unset, smart_format adds punctuation; false turns it off even with smart_format.

utt_splitnumber0.8

Seconds to wait before detecting a pause between words in submitted audio

paragraphstrue or falsefalse

Splits audio into paragraphs to improve transcript readability

utterancestrue or falsefalse

Segments speech into meaningful semantic units

filler_wordstrue or falsefalse

Filler Words can help transcribe interruptions in your audio, like "uh" and "um"

measurementstrue or falsefalse

Spoken measurements will be converted to their corresponding abbreviations

multichanneltrue or falsefalse

Transcribe each audio channel independently

smart_formattrue or falsefalse

Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability

diarize_modelone of
latest, v1, v2
—

Select and enable a specific diarization model version.

detect_entitiestrue or falsefalse

Identifies and extracts key entities from content in submitted audio

detect_languageJSON—

Identifies the dominant language spoken in submitted audio

profanity_filtertrue or falsefalse

Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely

Same request in code

curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "deepgram",
    "model": "whisper-large",
    "input": {
      "url": "<url>"
    }
  }'

Frequently asked questions

How much does Whisper Large Speech to Text cost?

$0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

How do I use Whisper Large Speech to Text through an API?

Send `POST /v1/runs` with `"provider": "deepgram"`, `"model": "whisper-large"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

Do I need an account with Deepgram to use Whisper Large Speech to Text?

No. Spiral runs it on its own Deepgram account and charges your Spiral balance.

Can my AI agent use Whisper Large Speech to Text?

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.