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

Muse Code · Audio

How to Use Kokoro Hindi in Muse Code

Kokoro Hindi turns Hindi scripts into speech for lessons, explainers, and read-aloud content. Unlike Kokoro American English, it targets Hindi pronunciation.

Prompts to try with Kokoro Hindi in Muse Code

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

Read this project's README and draft a short Hindi introduction in Devanagari. Use Kokoro Hindi to narrate it, keeping the spoken script separate from your editing notes.

Kokoro HindiMuse Code
Try asking
  • Turn the latest changelog entry into a plain Hindi release announcement. Use Kokoro Hindi to generate separate recordings for the main changes, and save each transcript beside its audio.

  • Find the Hindi help articles in this project and prepare one for a read-aloud version. Use Kokoro Hindi to narrate it in separate passages, preserving the meaning and expanding abbreviations in the spoken script.

  • Take one Hindi lesson from this project and use Kokoro Hindi to generate a normal reading and a slightly slower reading of the same passage. Save both with the transcript for listening review.

  • Prepare Hindi voiceover scripts for this project's onboarding tutorial. Use Kokoro Hindi to generate one recording per tutorial section, and list product names that need a pronunciation check.

How to set up Kokoro Hindi in Muse Code

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

Use Spiral's MCP server

  1. Install Muse Code
    curl -fsSL https://dev.meta.ai/install.sh | bash
  2. Ask Muse to add the server

    Start muse and ask:

    Add the Spiral MCP server at https://api.spiral.ai/mcp
  3. Sign in

    In your terminal, run:

    muse mcp login spiral

Use the Spiral skill

  1. Send Muse Code 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 Kokoro Hindi

    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/kokoro/hindi",
        "input": {
          "prompt": "सपने वो नहीं जो हम सोते समय देखते हैं, सपने वो हैं जो हमें सोने नहीं देते।",
          "voice": "hf_alpha"
        }
      }'

Then paste one of the prompts above: Muse Code finds Kokoro Hindi on Spiral, shows the price and runs it.

Kokoro Hindi providers and prices

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

falAudio
Kokoro TTS (Hindi)
fal-ai/kokoro/hindi

Settings you can ask for

Kokoro Hindi works from your prompt. Ask Muse Code for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Voicehf_alpha, hf_beta, hm_omega, or hm_psi

Voice ID for the desired voice.

Speed0.1 to 51

Speed of the generated audio. Default is 1.0.

Every API field of Kokoro TTS (Hindi) is on its tool page: open its card above.

What can you do with Kokoro Hindi in Muse Code?

Create Hindi narration from your project's documentation, lessons, and release notes. Your coding agent can prepare spoken scripts, generate passages separately, and keep each recording beside its transcript.

Hindi lesson narration

Turn a finished lesson into spoken Hindi, generating each teaching section separately for review.

Product explainer voiceovers

Narrate a Hindi walkthrough of a product or service. Review product names and technical terms before adding the audio to video.

Help article audio

Offer a spoken Hindi version of a help article, with a separate passage for each task or explanation.

Daily spoken briefings

Convert an approved Hindi digest into audio for listeners who prefer a spoken update.

Short story narration

Generate Hindi narration for an original short story. Review passages individually before assembling the full reading.

Hindi listening exercises

Create spoken practice passages with a matching transcript. Compare normal and slower readings for the intended lesson.

Release announcement audio

Turn an approved Hindi release announcement into a spoken explanation of what changed and who it affects.

Questions about Kokoro Hindi in Muse Code

Can Muse Code use Kokoro Hindi?

Yes. Add Spiral to Muse Code as an MCP server, and Muse Code can find and run Kokoro Hindi like any built-in tool.

How much does Kokoro Hindi cost in Muse Code?

Each item in `prompt` adds $0.026. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your Muse Code plan is separate.

Do I need a fal account to use Kokoro Hindi in Muse Code?

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

How long does it take to set up Kokoro Hindi in Muse Code?

About two minutes: install Muse Code, then ask Muse to add the server, then sign in.

Does Muse Code wait while Kokoro Hindi runs?

Kokoro Hindi runs in the background. Muse Code starts the run, checks on it and gives you the audio when it's ready.

What is Kokoro Hindi useful for?

Use it to narrate Hindi lessons, explainers, help articles, and spoken summaries. Prepare the wording first, then generate speech from the finished script.

How should I write a script for Kokoro Hindi?

Start with Hindi in Devanagari, as the maker's example does. As an editing practice, keep narration instructions outside the spoken script and write numbers the way you want listeners to hear them.

How much text should I generate at once?

The maker recommends about 100–200 tokens for most voices and warns of rushing above 400 tokens. Those are synthesis tokens, not words, so divide long material into passages and listen before combining them.

How can I make the narration slower?

Lower the speaking speed and compare the same passage before and after the change. For a long script, also try shorter passages so you can judge pacing section by section.

What audio quality does the maker's implementation produce?

The reference implementation saves WAV audio at 24 kHz. Use that as a reference for the model's output, and check the actual generated file before editing or publishing it.

Get started

Start using Kokoro Hindi in Muse Code

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

Paste this into Muse Code:

Set up Muse Code

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