[Integrations](https://spiral.ai/integrations) › [Instinct](https://spiral.ai/integrations/instinct) › [Scribe v3](https://spiral.ai/integrations/instinct/scribe-v3)

# How to Use Scribe v3 in Instinct

Scribe v3 turns recorded meetings, interviews, and videos into transcripts with speaker labels and word timestamps. Compared with Scribe v2, it improves transcription accuracy and speaker labeling.

|  |  |
| --- | --- |
| Model | Scribe v3 |
| Available through | ElevenLabs |
| Category | Audio |
| Price | $0.004335 per run at the default inputs for 60 seconds of input. |
| Returns | json |
| Runs | In the background |
| Setup | About 2 minutes, with a Spiral API key |

## Prompts to try with Scribe v3 in Instinct

- Every weekday, use Scribe v3 to transcribe newly available team meeting recordings with speaker labels. Prepare a digest of decisions and stated action items with timestamps.
- Each morning, use Scribe v3 to transcribe new recorded support calls with two expected speakers. Summarize each reported problem and resolution, citing the relevant timestamps.
- Every Friday, use Scribe v3 to transcribe this week's interview recordings with speaker labels. Collect customer quotes by topic and include recording titles and timestamps.
- Whenever a new podcast episode recording is available, use Scribe v3 to transcribe it with sound cues retained. Draft chapter titles and a timestamped editing checklist.
- Each evening, use Scribe v3 to transcribe new English voice notes. Give each note a title and extract explicitly stated tasks without inventing deadlines.

## How to set up Scribe v3 in Instinct

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

### Use the Spiral skill

1. **Send Instinct 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. **Create an API key**: In the console, open API keys and create a key for Instinct. Copy it.

2. **Send Instinct this message**: Instinct reads Spiral's skill and asks for your API key.

```text
set up https://spiral.ai/SKILL.md
```

3. **Give Instinct the key**: When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

### 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 v3**: 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_v3",
    "input": {
      "file": "<file>"
    }
  }'
```

Then paste one of the prompts above: Instinct finds Scribe v3 on Spiral, shows the price and runs it.

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

## Scribe v3 tools and prices

- [Scribe v3](https://spiral.ai/tools/elevenlabs/scribe_v3) (ElevenLabs): $0.004335 per run at the default inputs for 60 seconds of input.

## 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 v3 in Instinct?

Turn recurring recordings into a consistent set of searchable notes. A scheduled agent can use Scribe v3 to transcribe new recordings and prepare timestamped summaries for review.

### Meeting decisions with supporting timestamps

Transcribe a recorded meeting with Scribe v3, then have your agent extract decisions and link each one to the relevant passage.

### Interview quote selection

Use Scribe v3 to separate interviewer and guest speech. Ask your agent to collect candidate quotes with timestamps for review against the recording.

### Podcast editing notes

Transcribe an episode with Scribe v3, then have your agent identify topic changes and passages to review during editing.

### Video caption drafts

Use Scribe v3 word timestamps as the basis for caption timing. Have your agent divide the transcript into readable caption lines.

### Lecture study notes

Transcribe a recorded lecture with Scribe v3. Ask your agent to organize the transcript into topics, definitions, and questions for review.

### Support call review

Use Scribe v3 speaker labels to distinguish turns in recorded calls. Have your agent extract the reported problem, proposed resolution, and supporting timestamps.

### Searchable voice notes

Turn recorded voice notes into text with Scribe v3, then ask your agent to add concise titles and topic labels.

### Sound cues for accessible transcripts

Keep Scribe v3 audio event tags when laughter, applause, or music helps explain a recording. Have your agent preserve those cues in the transcript draft.

## Overview

- [ElevenLabs](https://spiral.ai/providers/elevenlabs)
- [All Instinct guides](https://spiral.ai/integrations/instinct)

## Scribe v3 in other agents

- [Amp](https://spiral.ai/integrations/amp/scribe-v3)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/scribe-v3)
- [Claude](https://spiral.ai/integrations/claude-desktop/scribe-v3)
- [Claude Code](https://spiral.ai/integrations/claude-code/scribe-v3)
- [Cline](https://spiral.ai/integrations/cline/scribe-v3)
- [Codex](https://spiral.ai/integrations/codex/scribe-v3)
- [Cursor](https://spiral.ai/integrations/cursor/scribe-v3)
- [Devin](https://spiral.ai/integrations/devin/scribe-v3)
- [dots](https://spiral.ai/integrations/dots/scribe-v3)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/scribe-v3)
- [Gemini](https://spiral.ai/integrations/gemini/scribe-v3)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/scribe-v3)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/scribe-v3)
- [goose](https://spiral.ai/integrations/goose/scribe-v3)
- [Grok](https://spiral.ai/integrations/grok/scribe-v3)
- [Grok Build](https://spiral.ai/integrations/grok-build/scribe-v3)
- [Hermes](https://spiral.ai/integrations/hermes/scribe-v3)
- [Manus](https://spiral.ai/integrations/manus/scribe-v3)
- [Muse](https://spiral.ai/integrations/muse/scribe-v3)
- [Muse Code](https://spiral.ai/integrations/muse-code/scribe-v3)
- [n8n](https://spiral.ai/integrations/n8n/scribe-v3)
- [Notion](https://spiral.ai/integrations/notion/scribe-v3)
- [OpenClaw](https://spiral.ai/integrations/openclaw/scribe-v3)
- [opencode](https://spiral.ai/integrations/opencode/scribe-v3)
- [Perplexity](https://spiral.ai/integrations/perplexity/scribe-v3)
- [Raycast](https://spiral.ai/integrations/raycast/scribe-v3)
- [VS Code](https://spiral.ai/integrations/vscode/scribe-v3)
- [Windsurf](https://spiral.ai/integrations/windsurf/scribe-v3)
- [Zapier](https://spiral.ai/integrations/zapier/scribe-v3)

## More Instinct guides

- [Scribe v2](https://spiral.ai/integrations/instinct/scribe-v2)
- [Seed Audio 1.0](https://spiral.ai/integrations/instinct/seed-audio-1-0)
- [SAM Audio Visual Separation](https://spiral.ai/integrations/instinct/sam-audio-visual-separation)
- [Seed Speech TTS 2.0](https://spiral.ai/integrations/instinct/seed-speech-tts-2-0)
- [SAM Audio](https://spiral.ai/integrations/instinct/sam-audio)
- [Sonilo V1.1 Text to Music](https://spiral.ai/integrations/instinct/sonilo-v1-1-text-to-music)

## Questions about Scribe v3 in Instinct

**Can Instinct use Scribe v3?**

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Scribe v3 like any built-in tool.

**How much does Scribe v3 cost in Instinct?**

$0.004335 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Instinct plan is separate.

**Do I need an ElevenLabs account to use Scribe v3 in Instinct?**

You need no ElevenLabs account. Instinct uses one Spiral API key for every tool, and Spiral runs Scribe v3 on its own ElevenLabs account.

**How long does it take to set up Scribe v3 in Instinct?**

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

**Does Instinct wait while Scribe v3 runs?**

Scribe v3 runs in the background. Instinct starts the run, checks on it and gives you the json when it's ready.

**What is Scribe v3 best used for?**

Use Scribe v3 to transcribe recorded conversations, including meetings and interviews. Speaker labels and word timestamps help an agent turn the transcript into notes or locate passages in the recording.

**How does Scribe v3 improve on Scribe v2?**

ElevenLabs reports 27% lower word error rate across 102 languages on FLEURS, plus improved speaker labeling. Treat the benchmark as a comparison, then evaluate recordings that resemble your actual work.

**Does Scribe v3 translate speech into English?**

Scribe v3 transcribes speech in the language spoken. Ask your agent to translate the finished transcript as a separate step.

**Can Scribe v3 distinguish several speakers?**

Yes, Scribe v3 supports speaker labels for up to 32 speakers. Supplying the expected speaker count can help with predicting who speaks when.

**How long can a recording be?**

Scribe supports recordings up to 15 hours long. Split longer recordings into shorter sections before transcription.

