How to Use Universal-3.5 Pro in ChatGPT
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 ChatGPT
Copy an example into ChatGPT, or ask in your own words.
Transcribe the attached interview with Universal-3.5 Pro. It mixes Hindi and English; preserve both languages as spoken.
Use Universal-3.5 Pro to transcribe the attached product discussion. Give it this context: the speakers discuss PostgreSQL, Kubernetes, and OpenTelemetry.
Transcribe this English presentation practice recording with Universal-3.5 Pro, keeping filler words. Show me the transcript so I can check the hesitations against the audio.
Use Universal-3.5 Pro to transcribe this meeting recording with the agenda I pasted as context. After transcription, list decisions supported by the returned text.
Transcribe this recorded interview with Universal-3.5 Pro. Keep spoken numbers written as words so I can study how the speaker expresses quantities.
How to set up Universal-3.5 Pro in ChatGPT
Pick the way that suits you. Each takes about two minutes.
Use the ChatGPT connector
- Add a custom MCP server
In ChatGPT open Plugins, then Add › Add custom MCP server. Name it Spiral, paste this URL and keep Authentication on OAuth. Tick I understand and want to continue, then click Create.
https://api.spiral.ai/mcp
- Click Connect
ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.
- Sign in to Spiral and approve
Sign in, pick the organization ChatGPT should use and click Authorize. Spiral gives the connection its own API key; ChatGPT never sees it, and you can remove the connection under Settings › Connected apps.
Use the Spiral skill
- Send ChatGPT this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- 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: ChatGPT 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.
$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
Universal-3.5 Pro works from your audio URL and prompt. Ask ChatGPT for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Domain | medical-v1 | Enable domain-specific transcription models to improve accuracy for specialized terminology. | |
| Punctuate | on or off | on | Enable Automatic Punctuation, can be true or false |
| Redact pii | on or off | off | Redact PII from the transcribed text using the Redact PII model, can be true or false. |
| Format text | on or off | on | Enable Text Formatting, can be true or false |
| Temperature | 0 to 1 | Control the amount of randomness injected into the model's response. | |
| Audio end at | a whole number | The point in time, in milliseconds, to stop transcribing in your media file. | |
| Disfluencies | on or off | off | Transcribe Filler Words, like "umm", in your media file; can be true or false. |
| Multichannel | on or off | off | Enable Multichannel transcription, can be true or false. |
| Custom topics | on or off | This parameter does not currently have any functionality attached to it. | |
| Content safety | on or off | off | Enable Content Moderation, can be true or false |
| Iab categories | on or off | off | Enable Topic Detection, can be true or false |
| Redact pii sub | entity_name or hash | The replacement logic for detected PII, can be | |
| Speaker labels | on or off | off | Enable Speaker diarization, can be true or false. Requires |
| Auto highlights | on or off | off | Enable Key Phrases, either true or false |
| Audio start from | a whole number | The point in time, in milliseconds, to begin transcribing in your media file. | |
| Entity detection | on or off | off | Enable Entity Detection, can be true or false |
| Filter profanity | on or off | off | Filter profanity from the transcribed text, can be true or false. |
| Redact pii audio | on or off | off | Generate a copy of the original media file with spoken PII "beeped" out, can be true or false. |
| Speech threshold | 0 to 1 | Reject audio files that contain less than this fraction of speech. | |
| Remove audio tags | all or speaker | Universal-3.5 Pro generates rich transcripts that can include inline annotations such as audio event markers and speaker cues. | |
| Speakers expected | a whole number | Tells the speaker label model how many speakers it should attempt to identify. | |
| Language detection | on or off | Automatic language detection identifies the spoken language and routes the request to the best model. | |
| Sentiment analysis | on or off | off | Enable Sentiment Analysis, can be true or false. Requires |
| Redact pii audio quality | mp3 or wav | Controls the filetype of the audio created by redact_pii_audio. | |
| Content safety confidence | 25 to 100 | The confidence threshold for the Content Moderation model. | |
| Redact pii return unredacted | on or off | When set to | |
| Language confidence threshold | 0 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 ChatGPT?
Read recorded conversations in text, including conversations that mix supported languages. Add topic context for Universal-3.5 Pro, then ask your chat agent to work from the transcript.
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.
More on Universal-3.5 Pro and ChatGPT
Overview
Universal-3.5 Pro in other agents
Questions about Universal-3.5 Pro in ChatGPT
Can ChatGPT use Universal-3.5 Pro?
Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Universal-3.5 Pro like any built-in tool.
How much does Universal-3.5 Pro cost in ChatGPT?
$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 ChatGPT plan is separate.
Do I need an AssemblyAI account to use Universal-3.5 Pro in ChatGPT?
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 ChatGPT?
About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.
Does ChatGPT wait while Universal-3.5 Pro runs?
Universal-3.5 Pro runs in the background. ChatGPT 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.
Start using Universal-3.5 Pro in ChatGPT
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into ChatGPT:
set up https://spiral.ai/SKILL.md


