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

Gemini CLI · AudioReleased 2025-12-17

How to Use Grok Voice in Gemini CLI

Grok Voice answers recorded speech with a spoken reply, making it useful for support questions, tutoring, and conversation practice. It generates a contextual answer rather than simply reading a supplied script.

Prompts to try with Grok Voice in Gemini CLI

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

Use Grok Voice to answer the recorded onboarding question using our README as context. Request a two-sentence explanation suitable for a developer joining the project today.

Grok VoiceGemini CLI
Try asking
  • Use Grok Voice to respond to the recorded support question using our troubleshooting guide. Ask for one concrete next step and flag any reply that contradicts the guide.

  • Use Grok Voice with the recorded Spanish question about our app. Supply the relevant help text from the repository and request a Spanish answer under 60 words.

  • Use Grok Voice to rehearse a technical interview from the recorded answer. Supply the role requirements from our hiring document and request one critique followed by one question.

  • Use Grok Voice on our recorded question fixture. Inspect the returned WAV and verify that our response handler accepts an empty transcript without discarding the audio.

How to set up Grok Voice 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:

    gemini mcp add --scope user --transport http spiral https://api.spiral.ai/mcp
  2. Sign in

    Start gemini and run:

    /mcp auth spiral
  3. Check it

    In Gemini CLI, run /mcp. From your shell:

    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.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run Grok Voice

    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": "xai/grok-voice",
        "input": {
          "audio_url": "https://v3b.fal.media/files/b/0a8dd5a2/hS140ygvRuxn-eY_qPhlv_assets_test_input_service.wav"
        }
      }'

Then paste one of the prompts above: Gemini CLI finds Grok Voice on Spiral, shows the price and runs it.

Grok Voice providers and prices

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

falAudio

Settings you can ask for

Grok Voice works from your audio URL and prompt. Ask Gemini CLI for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Voicecarina, zagan, helix, orion, luna, iris, altair, zenith and 20 more

Built-in xAI voice for the agent's reply. Uses Grok's default voice when omitted.

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

What can you do with Grok Voice in Gemini CLI?

Add spoken answers to product help, onboarding, or practice tools with Grok Voice. A coding agent can use project documentation to prepare context and evaluate replies to recorded questions.

Spoken support replies

Answer a recorded product question using approved support information supplied in the instructions. Ask for the missing detail when the recording does not explain the problem.

Language conversation practice

Respond to a learner's recording in Spanish, French, German, or Japanese. Request a correction and a follow-up question to give the learner another turn.

Interview rehearsal

Use a recorded interview answer to request a spoken critique and the next practice question. Specify the role and the skill the interviewer should assess.

Sales objection practice

Have Grok Voice play a prospective customer responding to a recorded pitch. Supply the customer's priorities and ask for one realistic objection.

Spoken tutoring

Respond to a student's explanation of a math or science concept. Ask for a hint or a question that checks understanding before requesting the full explanation.

Voice message follow-ups

Prepare spoken replies to recorded questions reviewed during a scheduled check. Supply the relevant context and request one answer per recording.

Developer onboarding practice

Turn project documentation into context for answering a developer's recorded question. Request an explanation suitable for someone encountering the codebase for the first time.

Questions about Grok Voice in Gemini CLI

Can Gemini CLI use Grok Voice?

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

How much does Grok Voice cost in Gemini CLI?

Up to $0.06474 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 Grok Voice in Gemini CLI?

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

How long does it take to set up Grok Voice in Gemini CLI?

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

Does Gemini CLI wait while Grok Voice runs?

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

What does Grok Voice do with a recording?

It listens to the speech and generates a spoken response to it. Try it for answering a question, responding to a learner, or playing a role in a practice conversation.

Which languages does Grok Voice support?

The documentation lists more than 20 languages, including English, Spanish, French, German, Hindi, Japanese, and Portuguese. Grok Voice normally detects the language spoken and answers in that language.

How long can a recording be?

The input recording must be no longer than 10 minutes and no larger than 50 MB. Both limits apply to each recording.

What audio does Grok Voice return?

The spoken reply is a 24 kHz mono WAV recording. A transcript of the reply may also be returned, but it can be empty.

How should I guide a Grok Voice reply?

Include an example of the response you want, such as a short answer followed by one question. xAI says Grok Voice follows sample phrases closely.

Get started

Start using Grok Voice in Gemini CLI

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

Paste this into Gemini CLI:

Set up Gemini CLI

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