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

Gemini · Audio

How to Use Chatterbox HD in Gemini

Chatterbox HD turns English scripts into expressive narration or character dialogue, with voice cloning from a short recording. It produces 24 kHz audio, with optional upscaling to 48 kHz.

Prompts to try with Chatterbox HD in Gemini

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

Use Chatterbox HD to read: 'Welcome to the workshop. Today, we will build our first wooden birdhouse.' Start with emotional intensity and guidance both at 0.5.

Chatterbox HDGemini
Try asking
  • Generate this line with Chatterbox HD: 'The signal has stopped. Someone is still inside the station.' Use emotional intensity around 0.7 and guidance around 0.3 for a dramatic audition.

  • Write a 60-word English introduction to a podcast about urban gardening, then read it with Chatterbox HD using ordinary speech settings.

  • Use my voice reference from this conversation with Chatterbox HD to say: 'Thanks for joining us. We will be back next Tuesday.' Request audio upscaled to 48 kHz.

  • Create two readings of 'I thought you had forgotten' with Chatterbox HD. Use ordinary settings for the first and emotional intensity 0.7 with guidance 0.3 for the second so I can compare them.

How to set up Chatterbox HD in Gemini

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

Use the Gemini connector

  1. Open Connected Apps

    On your computer, go to gemini.google.com. At the bottom, click Settings › Connected Apps. If you don't see Connected Apps, click Personal Intelligence first, then Connected Apps.

  2. Add Spiral as a custom app

    Under Custom apps, click Add a custom app and paste this MCP server URL:

    https://api.spiral.ai/mcp
  3. Sign in to Spiral and approve

    Follow the on-screen instructions. Spiral opens: sign in, pick the organization and click Authorize. No API key.

Use the Spiral skill

  1. Send Gemini 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 Chatterbox HD

    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": "fal",
        "model": "resemble-ai/chatterboxhd/text-to-speech",
        "input": {
          "text": "My name is Maximus Decimus Meridius, commander of the Armies of the North, General of the Felix Legions and loyal servant to the true emperor, Marcus Aurelius. Father to a murdered son, husband to a murdered wife. And I will have my vengeance, in this life or the next."
        }
      }'

Then paste one of the prompts above: Gemini finds Chatterbox HD on Spiral, shows the price and runs it.

Chatterbox HD providers and prices

Spiral runs Chatterbox HD through fal. Open a card for today's price, with every fee included.

falAudio
Chatterboxhd · Text to Speech
resemble-ai/chatterboxhd/text-to-speech

Settings you can ask for

Chatterbox HD works from your audio URL. Ask Gemini for any of these in your prompt.

SettingAllowed valuesDefaultDescription
VoiceAurora, Blade, Britney, Carl, Cliff, Richard, Rico, Siobhan and 1 more

The voice to use for the TTS request. If neither voice nor audio are provided, a random voice will be used.

Exaggeration0.25 to 20.5

Controls emotion exaggeration. Range typically 0.25 to 2.0.

CFG0 to 10.5

Classifier-free guidance scale (CFG) controls the conditioning factor. Range typically 0.2 to 1.0. For expressive or dramatic speech, try lower cfg values (e.g. ~0.3) and increase exaggeration to around 0.7 or higher. If the reference speaker has a fast speaking style, lowering cfg to around 0.3 can improve pacing.

High quality audioon or offoff

If True, the generated audio will be upscaled to 48kHz. The generation of the audio will take longer, but the quality will be higher. If False, the generated audio will be 24kHz.

Seeda whole number from 00

Useful to control the reproducibility of the generated audio. Assuming all other properties didn't change, a fixed seed should always generate the exact same audio file. Set to 0 for random seed.

Temperature0.05 to 50.8

Controls the randomness of generation. Range typically 0.05 to 5.

Every API field of Chatterboxhd · Text to Speech is on its tool page: open its card above.

What can you do with Chatterbox HD in Gemini?

Turn an English draft into narration you can hear with Chatterbox HD. A chat assistant can prepare the spoken script and help you compare ordinary and dramatic readings.

Product walkthrough narration

Turn an English walkthrough script into spoken instructions. Start with ordinary speech settings and review each instruction for clarity.

Game dialogue auditions

Generate separate reads of a character's lines. Compare ordinary and more dramatic delivery before choosing a performance.

Podcast introductions

Create a spoken introduction from an approved English script, using a short recording of the host as the voice reference.

Training lesson voiceovers

Produce narration for individual lesson sections. Review the pacing before pairing the audio with slides or demonstrations.

Spoken daily briefings

Convert a prepared English summary into a listening edition for a morning or evening briefing.

Ad script auditions

Hear how the same copy sounds with ordinary and heightened emotional delivery. Check whether greater intensity makes the message feel rushed.

Short story narration

Create spoken readings of English story passages using a narrator reference. Audition dramatic settings on tense scenes before applying them more widely.

Questions about Chatterbox HD in Gemini

Can Gemini use Chatterbox HD?

Yes. Add Spiral to Gemini as an MCP server, and Gemini can find and run Chatterbox HD like any built-in tool.

How much does Chatterbox HD cost in Gemini?

Each item in `text` adds $0.052. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Gemini plan is separate.

Do I need a fal account to use Chatterbox HD in Gemini?

No. Spiral runs Chatterbox HD on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up Chatterbox HD in Gemini?

About two minutes: open Connected Apps, then add Spiral as a custom app, then sign in to Spiral and approve.

Does Gemini wait while Chatterbox HD runs?

Chatterbox HD runs in the background. Gemini starts the run, checks on it and gives you the audio when it's ready.

Which languages does Chatterbox HD support?

The HD documentation specifies English text only. Keep scripts in English.

Does Chatterbox HD generate native 48 kHz audio?

The higher-quality setting upscales the generated audio to 48 kHz. Without it, output is 24 kHz.

What makes a good voice reference for Chatterbox HD?

Use a clean recording of one speaker. Chatterbox HD can clone from short audio, so choose a clear excerpt without competing voices.

How should I tune Chatterbox HD for dramatic dialogue?

Try emotional exaggeration around 0.7 and guidance around 0.3. Compare the result with an ordinary read before increasing the intensity further.

Why does a more expressive Chatterbox HD read sound faster?

Higher exaggeration tends to accelerate speech. Lowering guidance can help restore slower, more deliberate pacing.

Get started

Start using Chatterbox HD in Gemini

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

Paste this into Gemini:

Set up Gemini

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