Spiral gives your agent every tool with one account. Browse the tools →

ChatGPT · AudioReleased 2024-12-18

How to Use Eleven Flash v2.5 in ChatGPT

Eleven Flash v2.5 turns text into speech for conversational replies, interactive apps, and bulk audio production. Unlike Eleven Flash v2, it supports 32 languages rather than English alone.

Prompts to try with Eleven Flash v2.5 in ChatGPT

Copy an example into ChatGPT, or ask in your own words.

Explain how a rainbow forms in about 120 words, then narrate it with Eleven Flash v2.5. Use short sentences and a steady delivery.

Eleven Flash v2.5ChatGPT
Try asking
  • Write five beginner Spanish listening questions and answers, then read them with Eleven Flash v2.5 using a native Spanish voice. Put a two-second pause before each answer.

  • Use Eleven Flash v2.5 to read this message: Your appointment is on December fourth at two thirty in the afternoon. Please arrive ten minutes early.

  • Write a short welcome message for a museum's audio guide and generate it with Eleven Flash v2.5. Make two readings with the same voice, one steadier and one with more emotional variation.

  • Write a 100-word introduction to growing basil in Vietnamese, then narrate it with Eleven Flash v2.5 using a native Vietnamese voice.

How to set up Eleven Flash v2.5 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.

    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.

    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 v2.5

    One request; the result comes back by polling or a webhook.

    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_5",
        "input": {
          "text": "<text>",
          "voice_id": "<voice_id>"
        }
      }'

Then paste one of the prompts above: ChatGPT finds Eleven Flash v2.5 on Spiral, shows the price and runs it.

Eleven Flash v2.5 providers and prices

Spiral runs Eleven Flash v2.5 through ElevenLabs. Open a card for today's price, with every fee included.

ElevenLabsAudio
Eleven Flash v2.5
eleven_flash_v2_5

Settings you can ask for

Eleven Flash v2.5 works from your text, next text, and previous text. Ask ChatGPT for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Seeda whole number

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.

Output formatalaw_8000, mp3_22050_32, mp3_24000_48, mp3_44100_128, mp3_44100_192, mp3_44100_32, mp3_44100_64, mp3_44100_96 and 20 moremp3_44100_128

Output format of the generated audio.

Use pvc as ivcon or off

Whether to use the IVC version of a professional voice. This may improve expressiveness and reduce latency.

Apply text normalizationauto, on, or offauto

This parameter controls text normalization with three modes: 'auto', 'on', and 'off'.

Optimize streaming latencya whole number

You can turn on latency optimizations at some cost of quality.

Apply language text normalizationon or offoff

This parameter controls language text normalization.

Every API field of Eleven Flash v2.5 is on its tool page: open its card above.

What can you do with Eleven Flash v2.5 in ChatGPT?

Turn an explanation, practice passage, or prepared message into speech you can listen to. A chat agent can edit the wording for spoken delivery before generating it with Eleven Flash v2.5.

Spoken support replies

Turn approved answers into short spoken responses with Eleven Flash v2.5. Expand reference numbers into the form callers should hear.

Game dialogue previews

Use Eleven Flash v2.5 to hear quest instructions and character lines during development before recording final performances.

Localized app instructions

Generate spoken onboarding instructions in supported languages with Eleven Flash v2.5, using a voice suited to each language.

Daily audio briefings

Convert a short daily summary into speech with Eleven Flash v2.5. Write dates and quantities in words before narration.

Help article audio

Create spoken editions of help articles with Eleven Flash v2.5, splitting longer text into requests below 40,000 characters.

Practice listening exercises

Turn short passages into listening exercises with Eleven Flash v2.5. Add a brief pause between a question and its answer.

Questions about Eleven Flash v2.5 in ChatGPT

Can ChatGPT use Eleven Flash v2.5?

Yes. Add Spiral to ChatGPT as an MCP server, and ChatGPT can find and run Eleven Flash v2.5 like any built-in tool.

How much does Eleven Flash v2.5 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 v2.5 in ChatGPT?

No. Spiral runs Eleven Flash v2.5 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 v2.5 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 v2.5 runs?

Eleven Flash v2.5 runs in the background. ChatGPT starts the run, checks on it and gives you the audio when it's ready.

What is Eleven Flash v2.5 good at?

It suits spoken chatbot replies, interactive app speech, and bulk conversion of written text into audio. Those are useful starting points for support responses, game dialogue, and recurring spoken summaries.

Which languages does Eleven Flash v2.5 support?

It supports 32 languages, including English, Spanish, French, Japanese, Hungarian, Norwegian, and Vietnamese. Use a voice native to the intended language and accent for better pronunciation.

How long can one Eleven Flash v2.5 generation be?

The limit is 40,000 input characters per request. ElevenLabs estimates about 40 minutes of audio at that length; actual duration depends on the script and delivery.

How should I prepare numbers and dates for Eleven Flash v2.5?

Write them as you want listeners to hear them before generating speech. For example, expand an ambiguous date into a month name and spell a phone number digit by digit.

How can I make the delivery steadier or more expressive?

Raise stability for steadier delivery or lower it for more emotional variation. Test a short passage first: very low values can sound erratic, while very high values can sound monotonous.

Get started

Start using Eleven Flash v2.5 in ChatGPT

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into ChatGPT:

Set up ChatGPT

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options