[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Scribe v2](https://spiral.ai/integrations/gemini-cli/scribe-v2)

# How to Use Scribe v2 in Gemini CLI

Scribe v2 turns recorded interviews, meetings, and videos into transcripts with word timestamps and speaker labels. Unlike Scribe v2 Realtime, it focuses on long, complex recordings.

|  |  |
| --- | --- |
| Model | Scribe v2 |
| Available through | ElevenLabs |
| Category | Audio |
| Price | $0.26 per hour of audio, per channel. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Scribe v2 in Gemini CLI

- Use Scribe v2 to transcribe recordings/product-review.mp3 with speaker labels. Then compare the requested changes with this repository and draft an implementation checklist with transcript timestamps.
- Transcribe recordings/demo.mp4 with Scribe v2. Then use the word timestamps to draft an SRT file and check that subtitle times increase throughout.
- Use Scribe v2 on recordings/architecture-interview.wav with No Verbatim mode off. Then draft an architecture decision record, linking each proposed decision to a timestamp.
- Use Scribe v2 to transcribe recordings/onboarding.mp3, specifying English as the spoken language. Then compare the transcript with docs/onboarding.md and propose corrections supported by timestamped excerpts.
- Transcribe recordings/research-session.mp3 with Scribe v2 and speaker labels. Then create a Markdown index of user problems with timestamps, keeping your interpretations separate from transcript quotations.

## How to set up Scribe v2 in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 Scribe v2**: 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": "elevenlabs",
    "model": "scribe_v2",
    "input": {
      "file": "<file>"
    }
  }'
```

Then paste one of the prompts above: Gemini CLI finds Scribe v2 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Scribe v2 tools and prices

- [Scribe v2](https://spiral.ai/tools/elevenlabs/scribe_v2) (ElevenLabs): $0.26 per hour of audio, per channel.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| file |  | — | A link to the audio or video file to transcribe (a Toolbox file link or a public https URL), sent to ElevenLabs as the file. At least 100 ms of audio and at most 500 MB; give a larger file as `source_url`. Exactly one of `file` and `source_url`. |
| seed | 0 to 2147483647 | — | If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same seed and parameters should return the same result. Determinism is not guaranteed. Must be an integer between 0 and 2147483647. |
| diarize |  | false | Whether to annotate which speaker is currently talking in the uploaded file. |
| source_url |  | — | The URL of an audio or video file for ElevenLabs to fetch and transcribe: hosted audio or video files, YouTube and TikTok video URLs and other video hosting services. Exactly one of `file` and `source_url`. |
| file_format | pcm_s16le_16, other | other | The format of input audio. Options are 'pcm_s16le_16' or 'other' For `pcm_s16le_16`, the input audio must be 16-bit PCM at a 16kHz sample rate, single channel (mono), and little-endian byte order. Latency will be lower than with passing an encoded waveform. |
| no_verbatim |  | false | If true, the transcription will not have any filler words, false starts and non-speech sounds. Only supported with scribe_v2 model. |

## What can you do with Scribe v2 in Gemini CLI?

Turn recorded project discussions into searchable evidence for implementation work. Your coding agent can use Scribe v2 timestamps and speaker labels to connect transcript excerpts to documentation and proposed changes.

### Interview transcripts for research

Use Scribe v2 to transcribe recorded interviews with speaker labels and timestamps, then have your agent organize excerpts by research question.

### Podcast caption drafts

Use Scribe v2 word timestamps as the basis for captions, then have your agent group words into readable subtitle lines.

### Meeting records

Create a speaker-labeled transcript with Scribe v2, then have your agent extract decisions and action items with references to the recording.

### Searchable lecture archives

Transcribe recorded lectures with Scribe v2, then have your agent build a topic index linked to transcript timestamps.

### Recorded call review

Use Scribe v2 to separate speakers in recorded calls, then have your agent collect timestamped examples for a reviewer to assess.

### Readable dictation

Use Scribe v2 with No Verbatim mode to turn spoken drafts into text with fewer fillers and repetitions.

### Multilingual content archives

Use Scribe v2 to create original-language transcripts of recordings in supported languages, then have your agent organize them for search or later translation.

## Overview

- [ElevenLabs](https://spiral.ai/providers/elevenlabs)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Scribe v2 in other agents

- [Amp](https://spiral.ai/integrations/amp/scribe-v2)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/scribe-v2)
- [Claude](https://spiral.ai/integrations/claude-desktop/scribe-v2)
- [Claude Code](https://spiral.ai/integrations/claude-code/scribe-v2)
- [Cline](https://spiral.ai/integrations/cline/scribe-v2)
- [Codex](https://spiral.ai/integrations/codex/scribe-v2)
- [Cursor](https://spiral.ai/integrations/cursor/scribe-v2)
- [Devin](https://spiral.ai/integrations/devin/scribe-v2)
- [dots](https://spiral.ai/integrations/dots/scribe-v2)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/scribe-v2)
- [Gemini](https://spiral.ai/integrations/gemini/scribe-v2)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/scribe-v2)
- [goose](https://spiral.ai/integrations/goose/scribe-v2)
- [Grok](https://spiral.ai/integrations/grok/scribe-v2)
- [Grok Build](https://spiral.ai/integrations/grok-build/scribe-v2)
- [Hermes](https://spiral.ai/integrations/hermes/scribe-v2)
- [Instinct](https://spiral.ai/integrations/instinct/scribe-v2)
- [Manus](https://spiral.ai/integrations/manus/scribe-v2)
- [Muse](https://spiral.ai/integrations/muse/scribe-v2)
- [Muse Code](https://spiral.ai/integrations/muse-code/scribe-v2)
- [n8n](https://spiral.ai/integrations/n8n/scribe-v2)
- [Notion](https://spiral.ai/integrations/notion/scribe-v2)
- [OpenClaw](https://spiral.ai/integrations/openclaw/scribe-v2)
- [opencode](https://spiral.ai/integrations/opencode/scribe-v2)
- [Perplexity](https://spiral.ai/integrations/perplexity/scribe-v2)
- [Raycast](https://spiral.ai/integrations/raycast/scribe-v2)
- [VS Code](https://spiral.ai/integrations/vscode/scribe-v2)
- [Windsurf](https://spiral.ai/integrations/windsurf/scribe-v2)
- [Zapier](https://spiral.ai/integrations/zapier/scribe-v2)

## More Gemini CLI guides

- [SAM Audio Visual Separation](https://spiral.ai/integrations/gemini-cli/sam-audio-visual-separation)
- [Scribe v3](https://spiral.ai/integrations/gemini-cli/scribe-v3)
- [SAM Audio](https://spiral.ai/integrations/gemini-cli/sam-audio)
- [Seed Audio 1.0](https://spiral.ai/integrations/gemini-cli/seed-audio-1-0)
- [Qwen3-TTS 1.7B Voice Design](https://spiral.ai/integrations/gemini-cli/qwen3-tts-1-7b-voice-design)
- [Seed Speech TTS 2.0](https://spiral.ai/integrations/gemini-cli/seed-speech-tts-2-0)

## Questions about Scribe v2 in Gemini CLI

**Can Gemini CLI use Scribe v2?**

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run Scribe v2 like any built-in tool.

**How much does Scribe v2 cost in Gemini CLI?**

$0.26 per hour of audio, per channel. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini CLI plan is separate.

**Do I need an ElevenLabs account to use Scribe v2 in Gemini CLI?**

No. Spiral runs Scribe v2 on its own ElevenLabs account. You sign in to Spiral once and never paste a key.

**How long does it take to set up Scribe v2 in Gemini CLI?**

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

**Does Gemini CLI wait while Scribe v2 runs?**

Scribe v2 runs in the background. Gemini CLI starts the run, checks on it and gives you the json when it's ready.

**What is Scribe v2 best for?**

Recorded interviews, meetings, podcasts, and videos that need searchable transcripts or captions. It is designed for long, complex recordings, while Scribe v2 Realtime targets live audio.

**Which languages does Scribe v2 support, and does it translate?**

Scribe v2 supports more than 90 languages and transcribes speech in the language spoken. Translation requires a separate step.

**Can Scribe v2 separate speakers?**

Scribe v2 supports speaker diarization for up to 32 speakers. Review labels where people interrupt or speak over one another.

**How long can a recording be?**

ElevenLabs documents up to 15 hours per recording in standard transcription mode.

**Can Scribe v2 remove ums and repeated phrases?**

Yes. No Verbatim mode removes filler words, repeated phrases, and stuttering; keep it off when you need to study the original wording and delivery.

