[Integrations](https://spiral.ai/integrations) › [goose](https://spiral.ai/integrations/goose) › [Universal-3.5 Pro](https://spiral.ai/integrations/goose/universal-3-5-pro)

# How to Use Universal-3.5 Pro in goose

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.

|  |  |
| --- | --- |
| Model | Universal-3.5 Pro |
| Available through | AssemblyAI |
| Category | Audio |
| Price | $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. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Universal-3.5 Pro in goose

- 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.
- 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 goose

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

### Use Spiral's MCP server

1. **Add the extension**: In goose Desktop, open the sidebar, click Extensions, then Add custom extension. Enter:

2. **Sign in**: When goose first connects to Spiral, your browser opens. Sign in to Spiral, pick the organization and click Authorize. No API key. If the browser does not open, goose prints the link to open yourself.

### Use the Spiral skill

1. **Send goose 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.

```bash
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.

```bash
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: goose finds Universal-3.5 Pro on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/goose

## Universal-3.5 Pro tools and prices

- [Universal-3.5 Pro Speech to Text](https://spiral.ai/tools/assemblyai/universal-3-5-pro) (AssemblyAI): $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.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| domain | medical-v1 | — | Enable domain-specific transcription models to improve accuracy for specialized terminology. |
| prompt |  | — | Provide natural language prompting of up to 1,500 words of contextual information to the model. |
| topics |  | — | This parameter does not currently have any functionality attached to it. |
| punctuate |  | true | Enable [Automatic Punctuation](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false |
| redact_pii |  | false | Redact PII from the transcribed text using the Redact PII model, can be true or false. |
| format_text |  | true | Enable [Text Formatting](https://www.assemblyai.com/docs/pre-recorded-audio), can be true or false |

## What can you do with Universal-3.5 Pro in goose?

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.

## Overview

- [AssemblyAI](https://spiral.ai/providers/assemblyai)
- [All goose guides](https://spiral.ai/integrations/goose)

## Universal-3.5 Pro in other agents

- [Amp](https://spiral.ai/integrations/amp/universal-3-5-pro)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/universal-3-5-pro)
- [Claude](https://spiral.ai/integrations/claude-desktop/universal-3-5-pro)
- [Claude Code](https://spiral.ai/integrations/claude-code/universal-3-5-pro)
- [Cline](https://spiral.ai/integrations/cline/universal-3-5-pro)
- [Codex](https://spiral.ai/integrations/codex/universal-3-5-pro)
- [Cursor](https://spiral.ai/integrations/cursor/universal-3-5-pro)
- [Devin](https://spiral.ai/integrations/devin/universal-3-5-pro)
- [dots](https://spiral.ai/integrations/dots/universal-3-5-pro)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/universal-3-5-pro)
- [Gemini](https://spiral.ai/integrations/gemini/universal-3-5-pro)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/universal-3-5-pro)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/universal-3-5-pro)
- [Grok](https://spiral.ai/integrations/grok/universal-3-5-pro)
- [Grok Build](https://spiral.ai/integrations/grok-build/universal-3-5-pro)
- [Hermes](https://spiral.ai/integrations/hermes/universal-3-5-pro)
- [Instinct](https://spiral.ai/integrations/instinct/universal-3-5-pro)
- [Manus](https://spiral.ai/integrations/manus/universal-3-5-pro)
- [Muse](https://spiral.ai/integrations/muse/universal-3-5-pro)
- [Muse Code](https://spiral.ai/integrations/muse-code/universal-3-5-pro)
- [n8n](https://spiral.ai/integrations/n8n/universal-3-5-pro)
- [Notion](https://spiral.ai/integrations/notion/universal-3-5-pro)
- [OpenClaw](https://spiral.ai/integrations/openclaw/universal-3-5-pro)
- [opencode](https://spiral.ai/integrations/opencode/universal-3-5-pro)
- [Perplexity](https://spiral.ai/integrations/perplexity/universal-3-5-pro)
- [Raycast](https://spiral.ai/integrations/raycast/universal-3-5-pro)
- [VS Code](https://spiral.ai/integrations/vscode/universal-3-5-pro)
- [Windsurf](https://spiral.ai/integrations/windsurf/universal-3-5-pro)
- [Zapier](https://spiral.ai/integrations/zapier/universal-3-5-pro)

## More goose guides

- [Universal-3 Pro](https://spiral.ai/integrations/goose/universal-3-pro)
- [VEED Clean Audio](https://spiral.ai/integrations/goose/veed-clean-audio)
- [Universal-2](https://spiral.ai/integrations/goose/universal-2)
- [Whisper Large](https://spiral.ai/integrations/goose/whisper-large)
- [Stable Audio 3 Small SFX Text to Audio](https://spiral.ai/integrations/goose/stable-audio-3-small-sfx-text-to-audio)
- [Zonos2](https://spiral.ai/integrations/goose/zonos2)

## Questions about Universal-3.5 Pro in goose

**Can goose use Universal-3.5 Pro?**

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

**How much does Universal-3.5 Pro cost in goose?**

$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 goose plan is separate.

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

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 goose?**

About two minutes: add the extension, then sign in.

**Does goose wait while Universal-3.5 Pro runs?**

Universal-3.5 Pro runs in the background. goose 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.

