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

opencode · AudioReleased 2026-07-07

How to Use Universal-3.5 Pro in opencode

Universal-3.5 Pro transcribes recorded conversations, including speech that switches between 18 languages. Context about the topic, names, and terminology helps it resolve words that sound alike.

Prompts to try with Universal-3.5 Pro in opencode

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

Use Universal-3.5 Pro to transcribe recordings/design-review.mp3. Build a short contextual description from README.md and the architecture docs, focusing on component and project names.

Universal-3.5 Proopencode
Try asking
  • Transcribe recordings/customer-call.wav with Universal-3.5 Pro. The participants occupy separate audio channels; preserve channel information and save the transcript beside the recording.

  • Use Universal-3.5 Pro on recordings/demo.mp4. Supply product names from the project documentation as context, then compare the transcript with docs/demo-script.md.

  • Transcribe recordings/research-interview.mp3 with Universal-3.5 Pro, preserving its English and Spanish passages. Afterward, use the transcript to draft research notes in the project.

  • Use Universal-3.5 Pro to transcribe recordings/presentation-practice.wav with English filler words retained. Save the text for manual review and keep spoken numbers written as words.

How to set up Universal-3.5 Pro in opencode

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

Use Spiral's MCP server

  1. Add the server

    Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.

    opencode mcp add spiral --global --url https://api.spiral.ai/mcp
  2. Sign in

    Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.

    opencode mcp auth spiral
  3. Check it

    Spiral shows as connected.

    opencode mcp list

Use the Spiral skill

  1. Send opencode 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-3.5 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-3-5-pro",
        "input": {
          "audio_url": "<audio_url>"
        }
      }'

Then paste one of the prompts above: opencode finds Universal-3.5 Pro on Spiral, shows the price and runs it.

Universal-3.5 Pro providers and prices

Spiral runs Universal-3.5 Pro through AssemblyAI. Open a card for today's price, with every fee included.

AssemblyAIDeprecatedAudio

Settings you can ask for

Universal-3.5 Pro works from your audio URL and prompt. Ask opencode 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, can be true or false

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-3.5 Pro Speech to Text is on its tool page: open its card above.

What can you do with Universal-3.5 Pro in opencode?

Turn recorded project discussions into transcripts you can compare with the code and documentation. Give Universal-3.5 Pro relevant project terminology, then use the returned text for your agent's analysis.

Bilingual interview transcripts

Transcribe interviews that switch between supported languages, preserving the language of each spoken passage.

Technical meeting records

Supply the agenda and relevant project names as context, then transcribe the discussion for later reference.

Customer support call review

Describe the products and terminology discussed before transcribing calls for an agent to review.

Recruiting interview records

Provide candidate names, organizations, and role terminology as context for recorded interviews.

Separate-channel call transcripts

Transcribe call recordings with participants on separate channels while retaining channel information.

English speech coaching

Keep filler words in practice recordings for manual review of hesitation patterns. Verify examples against the audio before drawing conclusions.

Transcript-based meeting notes

Create a transcript with relevant meeting context, then have an agent extract decisions and action items from the returned text.

Questions about Universal-3.5 Pro in opencode

Can opencode use Universal-3.5 Pro?

Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Universal-3.5 Pro like any built-in tool.

How much does Universal-3.5 Pro cost in opencode?

$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 opencode plan is separate.

Do I need an AssemblyAI account to use Universal-3.5 Pro in opencode?

No. Spiral runs Universal-3.5 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-3.5 Pro in opencode?

About two minutes: add the server, then sign in, then check it.

Does opencode wait while Universal-3.5 Pro runs?

Universal-3.5 Pro runs in the background. opencode starts the run, checks on it and gives you the json when it's ready.

Which languages does Universal-3.5 Pro transcribe?

It supports 18 languages: English, Spanish, French, German, Italian, Portuguese, Arabic, Danish, Dutch, Finnish, Hebrew, Hindi, Japanese, Mandarin, Norwegian, Swedish, Turkish, and Vietnamese.

Can Universal-3.5 Pro handle two languages in one sentence?

Yes, when both are supported languages. It preserves words in the language spoken, including switches within a sentence.

What should I put in the contextual prompt?

Describe the conversation's topic and include relevant names, products, or technical vocabulary. Keep the description focused on what the speakers discuss; the limit is 1,500 words.

Does Universal-3.5 Pro produce summaries?

Use its transcript as the source for a separate summary or extraction step. Ask your agent to create notes or action items after transcription.

How long can a recording be?

AssemblyAI documents a batch transcription limit of 10 hours and 5 GB per request, with a minimum duration of 160 milliseconds. Split longer recordings before transcription.

Get started

Start using Universal-3.5 Pro in opencode

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

Paste this into opencode:

Set up opencode

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