[Integrations](https://spiral.ai/integrations) › [Claude Code](https://spiral.ai/integrations/claude-code) › [ElevenLabs Scribe v1](https://spiral.ai/integrations/claude-code/elevenlabs-scribe-v1)

# How to Use ElevenLabs Scribe v1 in Claude Code

ElevenLabs Scribe v1 transcribes recordings with word timestamps, speaker labels, and sound-event tags. Scribe v2 improves accuracy and stability on long recordings, pauses, and extended silences.

|  |  |
| --- | --- |
| Model | ElevenLabs Scribe v1 |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.039 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 ElevenLabs Scribe v1 in Claude Code

- Use ElevenLabs Scribe v1 to transcribe recordings/interview.mp3 in this project with speaker labeling. Save the original response and build a transcript view that seeks playback to each word's timestamp.
- Use ElevenLabs Scribe v1 to transcribe recordings/demo.wav as English. Generate a draft SRT file from the word timestamps and preserve the original transcript for review.
- Use ElevenLabs Scribe v1 on the podcast recording in this project with speaker labeling and sound-event tagging. Create an editing report with timestamped excerpts and separate sound cues from spoken text.
- Use ElevenLabs Scribe v1 to transcribe recordings/research-interview.m4a with anonymous speaker labels. Build a searchable quote index that retains each quote's timestamp and speaker label.
- Use ElevenLabs Scribe v1 to transcribe recordings/meeting.mp3. Then draft action items in the project's meeting notes, citing transcript timestamps and leaving speaker names unassigned unless confirmed.

## How to set up ElevenLabs Scribe v1 in Claude Code

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

### Use Spiral's MCP server

1. **Add the hosted server**: This adds Spiral to the current project. Add `--scope user` to use it in every project.

```bash
claude mcp add --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `claude`, type `/mcp`, choose spiral and Authenticate. Sign in to Spiral in the browser and click Authorize. No API key.

### Use the Spiral skill

1. **Send Claude Code 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 ElevenLabs Scribe v1**: 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": "fal",
    "model": "fal-ai/elevenlabs/speech-to-text",
    "input": {
      "audio_url": "https://v3.fal.media/files/zebra/zJL_oRY8h5RWwjoK1w7tx_output.mp3"
    }
  }'
```

Then paste one of the prompts above: Claude Code finds ElevenLabs Scribe v1 on Spiral, shows the price and runs it.

Setup guide in the docs: https://spiral.ai/docs/quickstarts/claude-code

## ElevenLabs Scribe v1 tools and prices

- [ElevenLabs Speech to Text · Scribe V1](https://spiral.ai/tools/fal/fal-ai/elevenlabs/speech-to-text) (fal): $0.039 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| language_code |  | — | Language code of the audio |
| tag_audio_events |  | true | Tag audio events like laughter, applause, etc. |
| diarize |  | true | Whether to annotate who is speaking |

## What can you do with ElevenLabs Scribe v1 in Claude Code?

Build searchable transcripts and caption drafts from recordings in your project. Have the coding agent use word timestamps and speaker labels to connect transcript text to playback.

### Meeting records with traceable decisions

Transcribe a recorded meeting with speaker labels. Have your agent extract decisions and action items, linking each one to its supporting timestamp.

### Interview quote review

Create a speaker-labeled interview transcript, then ask your agent to collect relevant quotes with timestamps for checking against the recording.

### Podcast editing notes

Use word timestamps and sound-event tags to prepare an edit list. Have your agent mark candidate cuts and retain the surrounding transcript for context.

### Caption drafts

Turn a recording into timestamped text, then have your agent arrange it into caption lines. Keep relevant laughter and other sound cues for review.

### Lecture study notes

Transcribe a recorded lecture in its spoken language. Ask your agent to organize the transcript into study notes with timestamps for revisiting explanations.

### Recorded support call review

Separate speakers in a completed call transcript. Have your agent collect customer questions and responses with timestamped evidence, keeping identities unassigned until confirmed.

### Voice notes turned into tasks

Transcribe spoken notes, then ask your agent to draft a task list. Keep the original transcript alongside the list so inferred tasks can be checked.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Claude Code guides](https://spiral.ai/integrations/claude-code)

## ElevenLabs Scribe v1 in other agents

- [Amp](https://spiral.ai/integrations/amp/elevenlabs-scribe-v1)
- [ChatGPT](https://spiral.ai/integrations/chatgpt/elevenlabs-scribe-v1)
- [Claude](https://spiral.ai/integrations/claude-desktop/elevenlabs-scribe-v1)
- [Cline](https://spiral.ai/integrations/cline/elevenlabs-scribe-v1)
- [Codex](https://spiral.ai/integrations/codex/elevenlabs-scribe-v1)
- [Cursor](https://spiral.ai/integrations/cursor/elevenlabs-scribe-v1)
- [Devin](https://spiral.ai/integrations/devin/elevenlabs-scribe-v1)
- [dots](https://spiral.ai/integrations/dots/elevenlabs-scribe-v1)
- [Factory Droid](https://spiral.ai/integrations/factory-droid/elevenlabs-scribe-v1)
- [Gemini](https://spiral.ai/integrations/gemini/elevenlabs-scribe-v1)
- [Gemini CLI](https://spiral.ai/integrations/gemini-cli/elevenlabs-scribe-v1)
- [Google Antigravity](https://spiral.ai/integrations/antigravity/elevenlabs-scribe-v1)
- [goose](https://spiral.ai/integrations/goose/elevenlabs-scribe-v1)
- [Grok](https://spiral.ai/integrations/grok/elevenlabs-scribe-v1)
- [Grok Build](https://spiral.ai/integrations/grok-build/elevenlabs-scribe-v1)
- [Hermes](https://spiral.ai/integrations/hermes/elevenlabs-scribe-v1)
- [Instinct](https://spiral.ai/integrations/instinct/elevenlabs-scribe-v1)
- [Manus](https://spiral.ai/integrations/manus/elevenlabs-scribe-v1)
- [Muse](https://spiral.ai/integrations/muse/elevenlabs-scribe-v1)
- [Muse Code](https://spiral.ai/integrations/muse-code/elevenlabs-scribe-v1)
- [n8n](https://spiral.ai/integrations/n8n/elevenlabs-scribe-v1)
- [Notion](https://spiral.ai/integrations/notion/elevenlabs-scribe-v1)
- [OpenClaw](https://spiral.ai/integrations/openclaw/elevenlabs-scribe-v1)
- [opencode](https://spiral.ai/integrations/opencode/elevenlabs-scribe-v1)
- [Perplexity](https://spiral.ai/integrations/perplexity/elevenlabs-scribe-v1)
- [Raycast](https://spiral.ai/integrations/raycast/elevenlabs-scribe-v1)
- [VS Code](https://spiral.ai/integrations/vscode/elevenlabs-scribe-v1)
- [Windsurf](https://spiral.ai/integrations/windsurf/elevenlabs-scribe-v1)
- [Zapier](https://spiral.ai/integrations/zapier/elevenlabs-scribe-v1)

## More Claude Code guides

- [ElevenLabs Music v2](https://spiral.ai/integrations/claude-code/elevenlabs-music-v2)
- [ElevenLabs Scribe v2](https://spiral.ai/integrations/claude-code/elevenlabs-scribe-v2)
- [ElevenLabs Music](https://spiral.ai/integrations/claude-code/elevenlabs-music)
- [ElevenLabs Sound Effects](https://spiral.ai/integrations/claude-code/elevenlabs-sound-effects)
- [ElevenLabs Multilingual v2](https://spiral.ai/integrations/claude-code/elevenlabs-multilingual-v2)
- [ElevenLabs Sound Effects V2](https://spiral.ai/integrations/claude-code/elevenlabs-sound-effects-v2)

## Questions about ElevenLabs Scribe v1 in Claude Code

**Can Claude Code use ElevenLabs Scribe v1?**

Yes. Add Spiral to Claude Code as an MCP server, and Claude Code can find and run ElevenLabs Scribe v1 like any built-in tool.

**How much does ElevenLabs Scribe v1 cost in Claude Code?**

Up to $0.039 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 Claude Code plan is separate.

**Do I need a fal account to use ElevenLabs Scribe v1 in Claude Code?**

No. Spiral runs ElevenLabs Scribe v1 on its own fal account. You sign in to Spiral once and never paste a key.

**How long does it take to set up ElevenLabs Scribe v1 in Claude Code?**

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

**Does Claude Code wait while ElevenLabs Scribe v1 runs?**

ElevenLabs Scribe v1 runs in the background. Claude Code starts the run, checks on it and gives you the json when it's ready.

**How many languages does ElevenLabs Scribe v1 support?**

ElevenLabs Scribe v1 supports 99 languages. It can detect the spoken language automatically, though specifying a known language can sometimes improve transcription.

**Does ElevenLabs Scribe v1 translate speech into English?**

It transcribes speech in the language spoken. Ask your agent to translate the completed transcript as a separate step, keeping the original for reference.

**Can ElevenLabs Scribe v1 tell who said what?**

Speaker labeling separates different voices in the transcript. The labels are anonymous, so confirm identities before replacing them with people's names.

**Where does ElevenLabs Scribe v1 fall behind Scribe v2?**

ElevenLabs reports that Scribe v2 improves accuracy and stability on long recordings, pauses, changes in tone, and extended silences. When using Scribe v1, make those sections a priority for review.

**What should I include in a transcription request?**

State the spoken language when you know it, and explain whether you need speaker attribution or sound cues in the finished transcript. Give your agent separate instructions for any summary, translation, or caption formatting after transcription.

