[Integrations](https://spiral.ai/integrations) › [ChatGPT](https://spiral.ai/integrations/chatgpt) › [Eleven Flash v2](https://spiral.ai/integrations/chatgpt/eleven-flash-v2)

# How to Use Eleven Flash v2 in ChatGPT

Eleven Flash v2 turns English text into speech for conversational replies and interactive apps. It accepts up to 30,000 characters per request and supports phoneme tags for pronunciation control.

|  |  |
| --- | --- |
| Model | Eleven Flash v2 |
| Available through | ElevenLabs |
| Category | Audio |
| Price | $0.052 per 1,000 characters of `text`. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Eleven Flash v2 in ChatGPT

- Use Eleven Flash v2 to read this English message: Your appointment is on November twenty-third at ten thirty in the morning. Please arrive ten minutes early. Use normal speaking speed and start with stability at fifty percent.
- Explain how rain forms in about one hundred English words, then use Eleven Flash v2 to make a spoken version. Put a one-second pause between the explanation and a final recap.
- Use Eleven Flash v2 to make two spoken takes of this line: We found the missing notebook. Try stability at thirty-five percent and seventy percent, keeping the same voice.
- Use Eleven Flash v2 to read this English practice sentence: Madison mailed the map on Monday. Use a phoneme tag to specify Madison's pronunciation, then show me the text you sent.
- Write a brief English telephone greeting for a public library, then use Eleven Flash v2 to speak it. Start with stability at fifty percent, similarity at seventy-five percent, and style exaggeration at zero.

## How to set up Eleven Flash v2 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 Eleven Flash 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": "eleven_flash_v2",
    "input": {
      "text": "<text>",
      "voice_id": "<voice_id>"
    }
  }'
```

Then paste one of the prompts above: ChatGPT finds Eleven Flash v2 on Spiral, shows the price and runs it.

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

## Eleven Flash v2 tools and prices

- [Eleven Flash v2](https://spiral.ai/tools/elevenlabs/eleven_flash_v2) (ElevenLabs): $0.052 per 1,000 characters of `text`.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| seed |  | — | 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. |
| next_text |  | — | The text that comes after the text of the current request. |
| audio_effects |  | — | Audio effects applied to the generated audio. |
| language_code |  | — | Language code (ISO 639-1) used to enforce a language for the model and text normalization. |
| output_format | alaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96, opus_48000_128, opus_48000_192, opus_48000_32, opus_48000_64, opus_48000_96, pcm_16000, pcm_22050, pcm_24000, pcm_32000, pcm_44100, pcm_48000, pcm_8000, ulaw_8000, wav_16000, wav_22050, wav_24000, wav_32000, wav_44100, wav_48000, wav_8000 | mp3_44100_128 | Output format of the generated audio. |
| previous_text |  | — | The text that came before the text of the current request. |

## What can you do with Eleven Flash v2 in ChatGPT?

Turn an English explanation, practice sentence, or short briefing into something you can listen to. Prepare the wording for speech, then compare delivery settings on a short sample.

### Spoken support replies

Turn an approved English support response into speech. Spell out reference numbers and dates before generating the reply.

### Interactive game dialogue

Generate English character lines for a game prototype. Compare stability settings on the same line before rendering the remaining dialogue.

### Product walkthrough drafts

Create spoken drafts of English onboarding instructions so a team can review wording and pauses alongside the product.

### Daily audio briefings

Convert a short English summary of verified updates into a spoken briefing, with dates and quantities written out.

### Pronunciation practice

Create English practice sentences with phoneme tags for names or technical terms, then review the generated pronunciation.

### Telephone announcement drafts

Generate English opening messages, menu instructions, and service announcements. Prepare phone numbers as spoken digits.

### Listening copies of articles

Turn English articles into speech for listening review. Split text above 30,000 characters and provide surrounding passages to help continuity.

## Overview

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

## Eleven Flash v2 in other agents

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

## More ChatGPT guides

- [Demucs](https://spiral.ai/integrations/chatgpt/demucs)
- [Eleven Flash v2.5](https://spiral.ai/integrations/chatgpt/eleven-flash-v2-5)
- [DeepFilterNet 3](https://spiral.ai/integrations/chatgpt/deepfilternet-3)
- [Eleven Multilingual v2](https://spiral.ai/integrations/chatgpt/eleven-multilingual-v2)
- [Cohere Transcribe](https://spiral.ai/integrations/chatgpt/cohere-transcribe)
- [Eleven Music](https://spiral.ai/integrations/chatgpt/eleven-music)

## Questions about Eleven Flash v2 in ChatGPT

**Can ChatGPT use Eleven Flash v2?**

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Eleven Flash v2 like any built-in tool.

**How much does Eleven Flash v2 cost in ChatGPT?**

$0.052 per 1,000 characters of `text`. 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 Eleven Flash v2 in ChatGPT?**

No. Spiral runs Eleven Flash 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 Eleven Flash v2 in ChatGPT?**

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

**Does ChatGPT wait while Eleven Flash v2 runs?**

Eleven Flash v2 runs in the background. ChatGPT starts the run, checks on it and gives you the audio when it's ready.

**Does Eleven Flash v2 support languages other than English?**

No. Eleven Flash v2 supports English only.

**How much speech can Eleven Flash v2 generate at once?**

It accepts up to 30,000 characters per request, approximately 30 minutes of speech. Treat that duration as an estimate, not an exact target.

**What is Eleven Flash v2 best suited for?**

Its focus is speech for conversational replies and interactive apps. For narration where stable, high fidelity matters more than generation speed, ElevenLabs recommends Multilingual v2.

**How can I control pauses and pronunciation?**

Use SSML break tags for pauses up to three seconds. Eleven Flash v2 also supports SSML phoneme tags for words that need a specific pronunciation.

**Which voice settings should I adjust first?**

Start around 50% stability, 75% similarity, and zero style exaggeration. Lower stability when you want more emotional variation; raise it cautiously because high values can sound monotonous.

