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

# How to Use Scribe v3 in ChatGPT

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, no API key |

## Prompts to try with Scribe v3 in ChatGPT

- Use Scribe v3 to transcribe this recorded meeting with speaker labels. Then list the decisions and include a timestamp for each.
- Use Scribe v3 to transcribe this English interview with two expected speakers. Pull five candidate quotes from the guest and include timestamps so I can check them.
- Use Scribe v3 to transcribe this lecture in its original language. Then organize the transcript into topics and write five study questions.
- Use Scribe v3 to transcribe this podcast recording, keeping laughter and music cues. Then suggest chapter titles with timestamps.
- Use Scribe v3 to transcribe this voice memo in Spanish. Keep the original transcript, then provide a separate English translation.

## How to set up Scribe v3 in ChatGPT

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

### Use the ChatGPT connector

1. **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.

```text
https://api.spiral.ai/mcp
```

2. **Click Connect**: ChatGPT asks to connect Spiral. Connect takes you to Spiral in your browser.

3. **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

1. **Send ChatGPT 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 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: ChatGPT finds Scribe v3 on Spiral, shows the price and runs it.

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

## 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 ChatGPT?

Find useful passages in recorded conversations without reading the entire transcript. A chat agent can use Scribe v3 speaker labels and word timestamps to prepare notes and answer questions with references to the recording.

### 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 ChatGPT guides](https://spiral.ai/integrations/chatgpt)

## Scribe v3 in other agents

- [Amp](https://spiral.ai/integrations/amp/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)
- [Instinct](https://spiral.ai/integrations/instinct/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 ChatGPT guides

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

## Questions about Scribe v3 in ChatGPT

**Can ChatGPT use Scribe v3?**

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

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

$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 ChatGPT plan is separate.

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

No. Spiral runs Scribe v3 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 v3 in ChatGPT?**

About two minutes: add a custom MCP server, then click Connect, then sign in to Spiral and approve.

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

Scribe v3 runs in the background. ChatGPT 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.

