[Integrations](https://spiral.ai/integrations) › [Hermes](https://spiral.ai/integrations/hermes) › [Whisper Large](https://spiral.ai/integrations/hermes/whisper-large)

# How to Use Whisper Large in Hermes

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.

|  |  |
| --- | --- |
| Model | Whisper Large |
| Available through | Deepgram |
| Category | Audio |
| Price | $0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Whisper Large in Hermes

- Every morning, use Whisper Large to transcribe newly received English voice recordings. Prepare a separate task list based only on explicit requests and collect it for my review.
- Each Friday, use Whisper Large to transcribe new French interview recordings in French. Produce separate English summaries and retain timestamps for candidate quotations.
- Each evening, use Whisper Large to transcribe newly received English podcast recordings. Draft editing notes with timestamps and mark every selected quotation for audio review.
- Every Monday, use Whisper Large to transcribe new German lecture recordings in German. Create a separate study outline and five questions grounded in each transcript.
- Each morning, use Whisper Large to transcribe new English inventory voice notes with spoken numbers written as digits. List quantities for review without updating inventory records.

## How to set up Whisper Large in Hermes

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

### Use the Spiral skill

1. **Send Hermes 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 Spiral's MCP server

1. **Add the server and sign in**: Hermes opens your browser: sign in to Spiral and click Authorize. No API key. When Hermes asks Enable all tools? \[Y/n/select], answer Y: n cancels without saving the server, and select hides the tools you leave out.

```bash
hermes mcp add spiral \
  --url https://api.spiral.ai/mcp \
  --auth oauth \
  --connect-timeout 300
```

2. **Check it**: In a chat that was already open, run `/reload-mcp`.

```bash
hermes mcp list
hermes mcp test spiral
```

### 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 Whisper Large**: 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": "deepgram",
    "model": "whisper-large",
    "input": {
      "url": "<url>"
    }
  }'
```

Then paste one of the prompts above: Hermes finds Whisper Large on Spiral, shows the price and runs it.

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

## Whisper Large tools and prices

- [Whisper Large Speech to Text](https://spiral.ai/tools/deepgram/whisper-large) (Deepgram): $0.00624 per minute of audio, per channel. Redaction: $0.0026 per minute. Entity detection: $0.00221 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| extra |  | — | Arbitrary key-value pairs that are attached to the API response for usage in downstream processing |
| redact |  | false | Redaction removes sensitive information from your transcripts |
| search |  | — | Search for terms or phrases in submitted audio |
| diarize |  | false | Deprecated: use `diarize_model` instead. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0. |
| replace |  | — | Search for terms or phrases in submitted audio and replaces them |
| encoding | linear16, flac, mulaw, amr-nb, amr-wb, opus, speex, g729 | — | Specify the expected encoding of your submitted audio |

## What can you do with Whisper Large in Hermes?

Build a recurring transcription workflow for new recorded talks, interviews, or voice notes. Your scheduled agent can preserve each transcript, prepare derived notes, and collect passages that need review.

### 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.

## Overview

- [Deepgram](https://spiral.ai/providers/deepgram)
- [All Hermes guides](https://spiral.ai/integrations/hermes)

## Whisper Large in other agents

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

## More Hermes guides

- [VEED Clean Audio](https://spiral.ai/integrations/hermes/veed-clean-audio)
- [Zonos2](https://spiral.ai/integrations/hermes/zonos2)
- [Universal-3.5 Pro](https://spiral.ai/integrations/hermes/universal-3-5-pro)
- [xAI Text to Speech](https://spiral.ai/integrations/hermes/xai-text-to-speech)
- [Universal-3 Pro](https://spiral.ai/integrations/hermes/universal-3-pro)
- [Bria Fibo Lite structured prompt](https://spiral.ai/integrations/hermes/bria-fibo-lite-structured-prompt)

## Questions about Whisper Large in Hermes

**Can Hermes use Whisper Large?**

Yes. Add Spiral to Hermes as an MCP server, and Hermes can find and run Whisper Large like any built-in tool.

**How much does Whisper Large cost in Hermes?**

$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 Hermes plan is separate.

**Do I need a Deepgram account to use Whisper Large in Hermes?**

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 Hermes?**

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

**Does Hermes wait while Whisper Large runs?**

Whisper Large runs in the background. Hermes 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.

