How to Use Whisper Large in Claude
Whisper Large turns recorded speech into transcripts for interviews, lectures, and voice notes across many languages. It uses OpenAI's large-v2 model, so don't assume results match Whisper large-v3.
Prompts to try with Whisper Large in Claude
Copy an example into Claude, or ask in your own words.
Use Whisper Large to transcribe this English interview recording. Then list five candidate quotations with timestamps so I can check them against the audio.
Use Whisper Large to transcribe this French lecture in French. Then make a study outline and keep your explanations separate from the transcript.
Use Whisper Large to transcribe this English voice note with spoken numbers written as digits. Then extract the tasks I explicitly mentioned and leave missing deadlines unspecified.
Use Whisper Large to transcribe this Japanese recording. Keep the transcript in Japanese and provide a separate English summary.
Use Whisper Large to transcribe this English podcast excerpt. Draft captions from the word timings and give me a checklist of names and quotations to review.
How to set up Whisper Large in Claude
Pick the way that suits you. Each takes about two minutes.
Use the Claude connector
- Add Spiral to Claude
Click Add Spiral in Claude above. Claude opens Add custom connector with Spiral and its URL filled in; check them and click Continue. Without the link: in Claude open Customize › Connectors › Add › Add custom connector and paste this URL:
https://api.spiral.ai/mcp
- Keep the detected sign-in and click Add
Claude finds Spiral's sign-in by itself: leave Sign in now and Use Claude's published identity selected.
- Click Connect
The connector page opens. Connect takes you to Spiral in your browser.
Use the Spiral skill
- Send Claude 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 Whisper Large
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": "deepgram", "model": "whisper-large", "input": { "url": "<url>" } }'
Then paste one of the prompts above: Claude finds Whisper Large on Spiral, shows the price and runs it.
Whisper Large providers and prices
Spiral runs Whisper Large through Deepgram. Open a card for today's price, with every fee included.
$0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute.
Settings you can ask for
Whisper Large works from your URL. Ask Claude for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Diarize | on or off | off | Deprecated: use |
| Encoding | linear16, flac, mulaw, amr-nb, amr-wb, opus, speex, or g729 | Specify the expected encoding of your submitted audio | |
| Language | af, am, ar, as, az, ba, be, bg and 105 more | en | The BCP-47 language tag that hints at the primary spoken language. |
| Numerals | on or off | off | Numerals converts numbers from written format to numerical format |
| Dictation | on or off | off | Dictation mode for controlling formatting with dictated speech |
| Punctuate | on or off | Add punctuation and capitalization to the transcript Left unset, smart_format adds punctuation; false turns it off even with smart_format. | |
| Utt split | a number | 0.8 | Seconds to wait before detecting a pause between words in submitted audio |
| Paragraphs | on or off | off | Splits audio into paragraphs to improve transcript readability |
| Utterances | on or off | off | Segments speech into meaningful semantic units |
| Filler words | on or off | off | Filler Words can help transcribe interruptions in your audio, like "uh" and "um" |
| Measurements | on or off | off | Spoken measurements will be converted to their corresponding abbreviations |
| Multichannel | on or off | off | Transcribe each audio channel independently |
| Smart format | on or off | off | Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability |
| Diarize model | latest, v1, or v2 | Select and enable a specific diarization model version. | |
| Detect entities | on or off | off | Identifies and extracts key entities from content in submitted audio |
| Profanity filter | on or off | off | Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely |
Every API field of Whisper Large Speech to Text is on its tool page: open its card above.
What can you do with Whisper Large in Claude?
Turn recorded interviews, lessons, and voice notes into text you can inspect and reuse. Your chat agent can then organize the transcript into notes, questions, or quotations with timestamps for checking.
Interview transcripts for reporting
Use Whisper Large to draft a transcript of a recorded interview. Review selected quotations against the audio before including them in an article.
Podcast editing notes
Transcribe podcast audio with Whisper Large, then ask your agent to identify passages worth editing or quoting. Keep timestamps beside each selection.
Lecture study materials
Turn a recorded lecture into text with Whisper Large, then have your agent organize the transcript into study notes and questions.
Multilingual research interviews
Use Whisper Large for French, German, Hindi, or Japanese interview recordings. Select the spoken language and arrange review by someone who understands it.
Voice notes for project work
Transcribe recorded ideas with Whisper Large, then ask your agent to turn the transcript into a task list. Check names and quantities before acting.
Draft captions for recorded lessons
Use Whisper Large transcripts and word timings as the starting point for captions. Have your agent arrange the text into readable cues for review.
Searchable audio archives
Transcribe recorded talks with Whisper Large, then have your agent index the text with links to the original recordings and timestamps.
Whisper Large success rate and speed on Spiral
Success and speed over the last 24 hours, across every run of these tools on Spiral.
| Tool | Success | Median time | Runs |
|---|---|---|---|
| Whisper Large Speech to Text | 100.0% | 7.4s | 28 |
More on Whisper Large and Claude
Overview
Whisper Large in other agents
Questions about Whisper Large in Claude
Can Claude use Whisper Large?
Yes. Add Spiral to Claude as an MCP server, and Claude can find and run Whisper Large like any built-in tool.
How much does Whisper Large cost in Claude?
$0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Claude plan is separate.
Do I need a Deepgram account to use Whisper Large in Claude?
No. Spiral runs Whisper Large on its own Deepgram account. You sign in to Spiral once and never paste a key.
How long does it take to set up Whisper Large in Claude?
About two minutes: add Spiral to Claude, then keep the detected sign-in and click Add, then click Connect.
Does Claude wait while Whisper Large runs?
Whisper Large runs in the background. Claude starts the run, checks on it and gives you the json when it's ready.
Which Whisper version is Whisper Large?
Whisper Large maps to OpenAI's large-v2 model. Evaluate its transcripts directly rather than assuming results from large-v3 benchmarks apply.
Can Whisper Large transcribe languages other than English?
Yes. Supported languages include French, German, Hindi, and Japanese, but accuracy varies by language. Set the spoken language deliberately for each recording.
How well does Whisper Large handle accents and background noise?
Whisper was trained for improved robustness to accents, background noise, and technical language. Still, check difficult passages against the recording before quoting them.
Can Whisper Large invent words?
Yes. Whisper can produce text that nobody spoke, so a fluent transcript is not proof of accuracy. Review quotations, names, and important numbers against the audio.
How should I handle misspelled product or company names?
Use find and replace for a known, repeatable spelling error. Check the correction in context before applying it throughout a transcript.
Start using Whisper Large in Claude
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into Claude:
set up https://spiral.ai/SKILL.md


