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

Gemini CLI · AudioReleased 2026-02-04

How to Use MiniMax Speech 2.8 HD in Gemini CLI

MiniMax Speech 2.8 HD suits narration where voice quality matters, from lessons to video voiceovers. Choose it over MiniMax Speech 2.8 Turbo when quality takes priority over synthesis speed.

Prompts to try with MiniMax Speech 2.8 HD in Gemini CLI

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

Use MiniMax Speech 2.8 HD to narrate our README's quick-start explanation. Rewrite it for listening, omit code blocks, keep the script under 2,000 characters, and save the script and audio in docs/audio.

MiniMax Speech 2.8 HDGemini CLI
Try asking
  • Use MiniMax Speech 2.8 HD to turn our tutorial script into narration. Insert <#0.5#> between instructions that require a click, keep every clip under 2,000 characters, and save numbered clips.

  • Use MiniMax Speech 2.8 HD to render the game's short character lines. Add (sighs) only to the disappointed line, keep other reactions out, and save each line separately.

  • Read this paragraph aloud with MiniMax Speech 2.8 HD in a calm, warm voice and give me the MP3. Save the result in ./assets.

  • Make a 30-second podcast intro voiceover with MiniMax Speech 2.8 HD.

How to set up MiniMax Speech 2.8 HD 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 MiniMax Speech 2.8 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": "fal-ai/minimax/speech-2.8-hd",
        "input": {
          "prompt": "Hello world! Welcome to MiniMax'\''s new text to speech model <#0.1#> Speech 2.8 HD (laughs) now available on Fal!"
        }
      }'

Then paste one of the prompts above: Gemini CLI finds MiniMax Speech 2.8 HD on Spiral, shows the price and runs it.

MiniMax Speech 2.8 HD providers and prices

Spiral runs MiniMax Speech 2.8 HD through fal. Open a card for today's price, with every fee included.

falAudio
MiniMax Speech 2.8 HD · Text to Speech
fal-ai/minimax/speech-2.8-hd

Settings you can ask for

MiniMax Speech 2.8 HD works from your prompt. Ask Gemini CLI for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Language boostChinese, Chinese,Yue, English, Arabic, Russian, Spanish, French, Portuguese and 30 more

Enhance recognition of specified languages and dialects

Output formaturl or hexhex

Format of the output content (non-streaming only)

Every API field of MiniMax Speech 2.8 HD · Text to Speech is on its tool page: open its card above.

What can you do with MiniMax Speech 2.8 HD in Gemini CLI?

Create spoken walkthroughs, tutorial narration, and character lines from your project's text. A coding agent can prepare scripts, apply pronunciation replacements, and save the generated clips beside the relevant assets.

Product walkthrough narration

Turn a walkthrough script into spoken instructions. Insert pauses where viewers need time to follow an action.

Short course lessons

Create narration for individual lessons. Test technical terms in a short passage before generating the lesson.

Multilingual announcements

Render approved announcement scripts in English, Spanish, French, or Japanese. Keep each language's wording ready for speech.

Audio editions of articles

Create spoken editions of articles, splitting longer scripts into sections. Review pronunciation and the transitions between clips.

Conversational character lines

Generate individual character lines with occasional laughs or sighs. Render and review each line separately to refine delivery.

Spoken assistant replies

Give an assistant a spoken version of its approved text response. Expand ambiguous abbreviations before synthesis.

Daily audio briefings

Turn a prepared daily summary into a short spoken briefing. Use pronunciation replacements for recurring names and acronyms.

MiniMax Speech 2.8 HD success rate and speed on Spiral

Success and speed over the last 24 hours, across every run of these tools on Spiral.

Success rate
96.6%
Fastest median run time
13.7s
Runs, last 24 hours
179
ToolSuccessMedian timeRuns
MiniMax Speech 2.8 HD · Text to Speech96.6%13.7s179

Questions about MiniMax Speech 2.8 HD in Gemini CLI

Can Gemini CLI use MiniMax Speech 2.8 HD?

Yes. Add Spiral to Gemini CLI as an MCP server, and Gemini CLI can find and run MiniMax Speech 2.8 HD like any built-in tool.

How much does MiniMax Speech 2.8 HD cost in Gemini CLI?

$0.13 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 Gemini CLI plan is separate.

Do I need a fal account to use MiniMax Speech 2.8 HD in Gemini CLI?

No. Spiral runs MiniMax Speech 2.8 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 MiniMax Speech 2.8 HD in Gemini CLI?

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

Does Gemini CLI wait while MiniMax Speech 2.8 HD runs?

MiniMax Speech 2.8 HD runs in the background. Gemini CLI starts the run, checks on it and gives you the audio when it's ready.

What is MiniMax Speech 2.8 good for?

Use it to turn scripts into spoken narration, lessons, or conversational replies. MiniMax Speech 2.8 HD emphasizes quality, while MiniMax Speech 2.8 Turbo emphasizes synthesis speed.

Can MiniMax Speech 2.8 read a whole chapter?

MiniMax's standard HTTP speech request accepts fewer than 10,000 characters. For longer material, split the script at paragraph or section boundaries and check the joins.

Which languages can MiniMax Speech 2.8 speak?

MiniMax documents 40 languages, including English, Spanish, French, Japanese, Mandarin, and Cantonese. Prepare the script in the language you want spoken.

How do I make pauses and reactions sound intentional?

Place a marker such as <#0.5#> between spoken phrases for a half-second pause. Add reactions such as (laughs) or (sighs) sparingly, then listen to the result before adding more.

How should I handle names and abbreviations?

Use pronunciation replacements for names, technical terms, and abbreviations that need a specific reading. Replacements can use ordinary words or phonetic notation, so test a short sentence before rendering the full script.

Get started

Start using MiniMax Speech 2.8 HD 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