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

Devin · AudioReleased 2026-02-03

How to Use Universal-3 Pro in Devin

Universal-3 Pro transcribes recordings with instructions for terminology, verbatim speech, and mixed-language conversations. Use it when you need to guide how speech becomes text, including whether to retain hesitations and false starts.

Prompts to try with Universal-3 Pro in Devin

Copy an example into Devin, or ask in your own words.

Use Universal-3 Pro to transcribe recordings/customer-interview.wav. Build a short terminology prompt from the product names in README.md, then save the transcript alongside the recording.

Universal-3 ProDevin
Try asking
  • Transcribe recordings/usability-session.wav with Universal-3 Pro. Explicitly retain um, uh, hesitations, repeated words, and false starts so I can study where the participant struggled.

  • Use Universal-3 Pro on recordings/bilingual-demo.mp3. Preserve English and Spanish exactly as spoken, including switches within a sentence, and save the transcript in research/.

  • Transcribe recordings/architecture-review.mp3 with Universal-3 Pro. Supply relevant service names from docs/architecture.md as context, then draft a separate list of decisions supported by the transcript.

  • Use Universal-3 Pro to transcribe recordings/support-call.wav and attempt to tag beeps and hold music. Save the transcript and mark the sound tags for manual checking.

How to set up Universal-3 Pro in Devin

Pick the way that suits you. Each takes about two minutes.

Use Spiral's MCP server

  1. Add a custom MCP

    Open Customize › MCPs. Click + and choose New MCP. Fill in:

  2. Sign in to Spiral and approve

    In Customize › MCPs, open Spiral and choose Connect. Spiral opens: sign in, pick the organization and click Authorize. No API key.

  3. Check it

    On Spiral's configuration page, click Test tools. Devin lists Spiral's tools.

Use the Spiral skill

  1. Send Devin this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Universal-3 Pro

    One request; the result comes back by polling or a webhook.

    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>"
        }
      }'

Then paste one of the prompts above: Devin finds Universal-3 Pro on Spiral, shows the price and runs it.

Universal-3 Pro providers and prices

Spiral runs Universal-3 Pro through AssemblyAI. Open a card for today's price, with every fee included.

AssemblyAIDeprecatedAudio

Settings you can ask for

Universal-3 Pro works from your audio URL and prompt. Ask Devin for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Domainmedical-v1

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

Punctuateon or offon

Enable Automatic Punctuation, can be true or false

Redact piion or offoff

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

Format texton or offon

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

Temperature0 to 1

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

Audio end ata whole number

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

Disfluencieson or offoff

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

Multichannelon or offoff

Enable Multichannel transcription, can be true or false.

Custom topicson or off

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

Content safetyon or offoff

Enable Content Moderation, can be true or false

Iab categorieson or offoff

Enable Topic Detection, can be true or false

Redact pii subentity_name or hash

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

Speaker labelson or offoff

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

Auto highlightson or offoff

Enable Key Phrases, either true or false

Audio start froma whole number

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

Entity detectionon or offoff

Enable Entity Detection, can be true or false

Filter profanityon or offoff

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

Redact pii audioon or offoff

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

Speech threshold0 to 1

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

Remove audio tagsall or speaker

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

Speakers expecteda whole number

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

Language detectionon or off

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

Sentiment analysison or offoff

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

Redact pii audio qualitymp3 or wav

Controls the filetype of the audio created by redact_pii_audio.

Content safety confidence25 to 100

The confidence threshold for the Content Moderation model.

Redact pii return unredactedon or off

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

Language confidence threshold0 to 1

The confidence threshold for the automatically detected language.

Every API field of Universal-3 Pro Speech to Text is on its tool page: open its card above.

What can you do with Universal-3 Pro in Devin?

Turn recorded interviews and technical discussions into transcripts your project can use. Your coding agent can give Universal-3 Pro terminology from project documentation and use the resulting text to draft research notes.

Technical interview transcripts

Use Universal-3 Pro to transcribe engineering interviews with context about product names and technical terms.

Customer research

Preserve hesitations, repeated words, and false starts with Universal-3 Pro when exact phrasing matters to interview analysis.

Bilingual support calls

Use Universal-3 Pro for English-Spanish calls, asking it to retain each phrase in its spoken language.

Sales coaching

Transcribe recorded sales calls with Universal-3 Pro while retaining fillers and restarts for a coach to review.

Clinical conversation drafts

Give Universal-3 Pro relevant medication names and clinical terminology when preparing a transcript for human review.

Podcast transcript drafts

Use Universal-3 Pro to transcribe episodes with guest names and topic context supplied before transcription.

Call sound review

Test Universal-3 Pro on recorded calls with instructions to tag beeps or hold music. Check its experimental sound tags against the audio.

Questions about Universal-3 Pro in Devin

Can Devin use Universal-3 Pro?

Yes. Add Spiral to Devin as an MCP server, and Devin can find and run Universal-3 Pro like any built-in tool.

How much does Universal-3 Pro cost in Devin?

$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 from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Devin plan is separate.

Do I need an AssemblyAI account to use Universal-3 Pro in Devin?

No. Spiral runs Universal-3 Pro on its own AssemblyAI account. You sign in to Spiral once and never paste a key.

How long does it take to set up Universal-3 Pro in Devin?

About two minutes: add a custom MCP, then sign in to Spiral and approve, then check it.

Does Devin wait while Universal-3 Pro runs?

Universal-3 Pro runs in the background. Devin starts the run, checks on it and gives you the json when it's ready.

Which languages does Universal-3 Pro support?

Universal-3 Pro supports English, Spanish, German, French, Portuguese, and Italian. It can transcribe conversations that mix those languages.

Can Universal-3 Pro keep filler words and false starts?

Yes. Ask explicitly for fillers such as um and uh, hesitations, repeated words, and false starts so the transcript retains the speech patterns you need.

What should I put in a Universal-3 Pro prompt?

Give the recording's topic, relevant names, specialized terminology, and the transcript style you want. Keep the instructions within 1,500 words.

How long can a recording be?

AssemblyAI documents a maximum of 10 hours and 5 GB per batch transcription request, with a minimum duration of 160 milliseconds. Split recordings that exceed either maximum.

Are prompted speaker labels reliable on long recordings?

AssemblyAI warns that prompt-generated labels can become inconsistent when a long recording is processed in chunks. Review speaker assignments across the recording before relying on them.

Get started

Start using Universal-3 Pro in Devin

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into Devin:

Set up Devin

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options