[Integrations](https://spiral.ai/integrations) › [Gemini CLI](https://spiral.ai/integrations/gemini-cli) › [Chatterbox HD Speech to Speech](https://spiral.ai/integrations/gemini-cli/chatterbox-hd-speech-to-speech)

# How to Use Chatterbox HD Speech to Speech in Gemini CLI

Chatterbox HD Speech to Speech changes the voice in a recorded performance while retaining its words and delivery. It works from spoken audio and offers optional 48 kHz upscaling for the converted result.

|  |  |
| --- | --- |
| Model | Chatterbox HD Speech to Speech |
| Available through | fal |
| Category | Audio |
| Price | Up to $0.026 per run at the default inputs for 60 seconds of input. |
| Returns | audio |
| Runs | In the background |
| Setup | About 2 minutes, no API key |

## Prompts to try with Chatterbox HD Speech to Speech in Gemini CLI

- Use Chatterbox HD Speech to Speech to convert audio/tutorial-intro.wav with the supplied narrator reference. Save the result beside the original for review.
- Run Chatterbox HD Speech to Speech on the guard's recorded lines in assets/dialogue. Use the supplied character voice reference and keep each line as a separate output.
- Use Chatterbox HD Speech to Speech on audio/demo-read.wav. Generate one 24 kHz result and one 48 kHz upscaled result for comparison.
- Convert the recorded onboarding narration in this project with Chatterbox HD Speech to Speech using the supplied voice sample. Add the result to the audio preview page.
- Use Chatterbox HD Speech to Speech to audition the supplied target voice on assets/animation/robot-line.wav. Keep the source take available in the preview.

## How to set up Chatterbox HD Speech to Speech in Gemini CLI

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

### Use Spiral's MCP server

1. **Add the server**: Or add it to `~/.gemini/settings.json` yourself:

```bash
gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
```

2. **Sign in**: Start `gemini` and run:

```text
/mcp auth spiral
```

3. **Check it**: In Gemini CLI, run `/mcp`. From your shell:

```bash
gemini mcp list
```

### Use the Spiral skill

1. **Send Gemini CLI 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 Chatterbox HD Speech to Speech**: 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": "resemble-ai/chatterboxhd/speech-to-speech",
    "input": {
      "source_audio_url": "https://storage.googleapis.com/chatterbox-demo-samples/samples/duff_stewie.wav"
    }
  }'
```

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

Setup guide in the docs: https://spiral.ai/docs/quickstarts/gemini-cli

## Chatterbox HD Speech to Speech tools and prices

- [Chatterboxhd · Speech to Speech](https://spiral.ai/tools/fal/resemble-ai/chatterboxhd/speech-to-speech) (fal): $0.026 per minute.

## Settings you can ask for

| Setting | Allowed values | Default | Description |
| --- | --- | --- | --- |
| target_voice | Aurora, Blade, Britney, Carl, Cliff, Richard, Rico, Siobhan, Vicky | — | The voice to use for the speech-to-speech request. If neither target_voice nor target_voice_audio_url are provided, a random target voice will be used. |
| target_voice_audio_url |  | — | URL to the audio file which represents the voice of the output audio. If provided, this will override the target_voice setting. If neither target_voice nor target_voice_audio_url are provided, the default target voice will be used. |
| high_quality_audio |  | false | 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. |

## What can you do with Chatterbox HD Speech to Speech in Gemini CLI?

Create alternate voices for recorded dialogue and narration in your project. Use Chatterbox HD Speech to Speech to produce audio assets for review alongside the original recordings.

### Game dialogue auditions

Try another voice on a recorded character line before choosing a direction for the role.

### Tutorial narration

Convert a spoken walkthrough into the voice chosen for a product tutorial.

### Podcast intros

Revoice a recorded episode introduction and compare it with the original take.

### Animation voice tests

Use a recorded performance to audition voices for an animated character.

### Training narration

Convert recorded lesson segments into the selected course narrator's voice.

### Commercial voice-over auditions

Try different voices on an approved spoken ad read before selecting the final voice.

## Overview

- [fal](https://spiral.ai/providers/fal)
- [All Gemini CLI guides](https://spiral.ai/integrations/gemini-cli)

## Chatterbox HD Speech to Speech in other agents

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

## More Gemini CLI guides

- [Chatterbox HD](https://spiral.ai/integrations/gemini-cli/chatterbox-hd)
- [Chatterbox Multilingual](https://spiral.ai/integrations/gemini-cli/chatterbox-multilingual)
- [CassetteAI Sound Effects Generator](https://spiral.ai/integrations/gemini-cli/cassetteai-sound-effects-generator)
- [Chatterbox Speech to Speech](https://spiral.ai/integrations/gemini-cli/chatterbox-speech-to-speech)
- [CassetteAI Music Generator](https://spiral.ai/integrations/gemini-cli/cassetteai-music-generator)
- [Chatterbox TTS](https://spiral.ai/integrations/gemini-cli/chatterbox-tts)

## Questions about Chatterbox HD Speech to Speech in Gemini CLI

**Can Gemini CLI use Chatterbox HD Speech to Speech?**

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

**How much does Chatterbox HD Speech to Speech cost in Gemini CLI?**

Up to $0.026 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 Gemini CLI plan is separate.

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

No. Spiral runs Chatterbox HD Speech to Speech 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 Speech to Speech in Gemini CLI?**

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

**Does Gemini CLI wait while Chatterbox HD Speech to Speech runs?**

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

**What is Chatterbox HD Speech to Speech useful for?**

Use it to try a different voice on an existing spoken performance. Recorded narration, character dialogue, and voice-over auditions are practical starting points.

**Can it read a written script?**

Chatterbox HD Speech to Speech converts recorded speech. Record the script first, or choose a text-to-speech model when you want to start from writing.

**How should I control pauses and emphasis?**

Perform them in the source recording, since conversion preserves the original timing and delivery. If a pause or emphasis needs changing, revise the take before converting it.

**What sample rate does it produce?**

Output is 24 kHz without upscaling. The higher-quality option upscales the result to 48 kHz.

**Does the converted audio include a watermark?**

Yes. Chatterbox HD Speech to Speech includes built-in perceptual watermarking.

