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

AssemblyAIAudioAvailable nowReleased 2026-02-03

Universal-3 Pro Speech to Text

universal-3-pro

Transcribe audio and video to text with Universal-3 Pro Speech to Text from AssemblyAI through one Spiral API key. Transcribes audio or video into formatted text, steered by a written prompt or key terms, with speaker labels and PII redaction. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

Pricing

$0.273 per hour of audio, per channel. Features, per hour: speaker labels $0.026, key terms $0.065, translation $0.078, speaker identification $0.026, custom formatting $0.039, action items $0.026, summaries $0.026 ($0.091 at medium effort), entity detection $0.104, sentiment $0.026, key phrases $0.013, topic detection $0.195, content moderation $0.195, profanity filter $0.013, PII redaction $0.104, audio redaction $0.065, medical mode $0.195, custom prompt $0.065.

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
audio_url requiredURL or file—

The URL of the audio or video file to transcribe.

domainone of
medical-v1
—

Enable domain-specific transcription models to improve accuracy for specialized terminology.

prompttext—

Provide natural language prompting of up to 1,500 words of contextual information to the model.

topicslist—

This parameter does not currently have any functionality attached to it.

punctuatetrue or falsetrue

Enable Automatic Punctuation, can be true or false

redact_piitrue or falsefalse

Redact PII from the transcribed text using the Redact PII model, can be true or false.

format_texttrue or falsetrue

Enable Text Formatting. Universal-3 Pro always formats the text: false is refused.

temperaturenumber
0 to 1
—

Control the amount of randomness injected into the model's response.

audio_end_atnumber (whole)—

The point in time, in milliseconds, to stop transcribing in your media file.

disfluenciestrue or falsefalse

Transcribe Filler Words, like "umm", in your media file; can be true or false.

multichanneltrue or falsefalse

Enable Multichannel transcription, can be true or false.

custom_topicstrue or false—

This parameter does not currently have any functionality attached to it.

language_codeJSON—

The language of your audio file.

content_safetytrue or falsefalse

Enable Content Moderation, can be true or false

iab_categoriestrue or falsefalse

Enable Topic Detection, can be true or false

language_codeslist—

The language codes of your audio file. Used for Code switching One of the values specified must be en.

redact_pii_subone of
entity_name, hash
—

The replacement logic for detected PII, can be entity_name or hash. See PII redaction for more details.

speaker_labelstrue or falsefalse

Enable Speaker diarization, can be true or false. Requires punctuate to be true.

auto_highlightstrue or falsefalse

Enable Key Phrases, either true or false

custom_spellingJSON—

Customize how words are spelled and formatted using to and from values.

keyterms_promptlist—

Improve accuracy with up to 200 (for Universal-2) or 1000 (for Universal-3.5 Pro) domain-specific words or phrases (maximum 6 words per phrase).

speaker_optionsJSON—

Specify options for Speaker diarization.

audio_start_fromnumber (whole)—

The point in time, in milliseconds, to begin transcribing in your media file.

entity_detectiontrue or falsefalse

Enable Entity Detection, can be true or false

filter_profanitytrue or falsefalse

Filter profanity from the transcribed text, can be true or false.

redact_pii_audiotrue or falsefalse

Generate a copy of the original media file with spoken PII "beeped" out, can be true or false.

speech_thresholdnumber
0 to 1
—

Reject audio files that contain less than this fraction of speech.

remove_audio_tagsone of
all, speaker
—

Universal-3.5 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues.

speakers_expectednumber (whole)—

Tells the speaker label model how many speakers it should attempt to identify.

language_detectiontrue or false—

Automatic language detection identifies the spoken language and routes the request to the best model.

sentiment_analysistrue or falsefalse

Enable Sentiment Analysis, can be true or false. Requires punctuate to be true.

redact_pii_policieslist—

The list of PII Redaction policies to enable. See PII redaction for more details.

speech_understandingJSON—

Enable speech understanding tasks like Translation, Speaker Identification, and Custom Formatting.

redact_static_entitiesJSON—

A map of user-defined terms to redact, where each key is a redaction label and each value is a list of exact terms to match (e.g. { "INTERNAL_TOOL": ["Bearclaw", "Cubclaw"] }).

redact_pii_audio_optionsJSON—

Specify options for PII redacted audio files.

redact_pii_audio_qualityone of
mp3, wav
—

Controls the filetype of the audio created by redact_pii_audio.

content_safety_confidencenumber (whole)
25 to 100
—

The confidence threshold for the Content Moderation model.

language_detection_optionsJSON—

Specify options for Automatic Language Detection.

redact_pii_return_unredactedtrue or false—

When set to true, returns the original unredacted transcript alongside the redacted one in the same response.

language_confidence_thresholdnumber
0 to 1
—

The confidence threshold for the automatically detected language.

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": "assemblyai",
    "model": "universal-3-pro",
    "input": {
      "audio_url": "<audio_url>"
    }
  }'

Frequently asked questions

How much does Universal-3 Pro Speech to Text cost?

$0.273 per hour of audio, per channel. Features, per hour: speaker labels $0.026, key terms $0.065, translation $0.078, speaker identification $0.026, custom formatting $0.039, action items $0.026, summaries $0.026 ($0.091 at medium effort), entity detection $0.104, sentiment $0.026, key phrases $0.013, topic detection $0.195, content moderation $0.195, profanity filter $0.013, PII redaction $0.104, audio redaction $0.065, medical mode $0.195, custom prompt $0.065. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

How do I use Universal-3 Pro Speech to Text through an API?

Send `POST /v1/runs` with `"provider": "assemblyai"`, `"model": "universal-3-pro"` 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 AssemblyAI to use Universal-3 Pro Speech to Text?

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

Can my AI agent use Universal-3 Pro Speech to Text?

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