How to Use Kokoro American English in opencode
Kokoro American English turns written scripts into US English speech for explainers, lessons, and narrated updates. Use it for paragraph-length narration, and split longer scripts to reduce rushed delivery.
Prompts to try with Kokoro American English in opencode
Copy an example into opencode, or ask in your own words.
Read the README and draft a short spoken introduction to the project. Generate it with Kokoro American English at normal speed, keeping code snippets out of the narration.
Use the latest changelog to write a spoken summary of three user-facing changes. Generate separate passages with Kokoro American English and save the scripts beside the audio.
Turn the onboarding guide into a narrated walkthrough with Kokoro American English. Divide it at topic boundaries and keep the same voice throughout.
Find the demo script in this project. Generate one passage with Kokoro American English at speed 1.0 and again at 0.9 so I can compare the pacing.
Review the tutorial files and draft a spoken explanation of the main workflow. Use Kokoro American English for the narration, splitting long passages before generation.
How to set up Kokoro American English in opencode
Pick the way that suits you. Each takes about two minutes.
Use Spiral's MCP server
- Add the server
Leave out --global to add Spiral to the current project only. No header and no client ID or secret: opencode registers itself with Spiral.
opencode mcp add spiral --global --url https://api.spiral.ai/mcp
- Sign in
Your browser opens. Sign in to Spiral, pick the organization and click Authorize, then return to the terminal. No API key. Inside opencode, /mcps starts the same sign-in.
opencode mcp auth spiral
- Check it
Spiral shows as connected.
opencode mcp list
Use the Spiral skill
- Send opencode this message
Your agent reads Spiral's skill and sets itself up.
set up https://spiral.ai/SKILL.md
- Sign in or paste a key
Approve Spiral in the browser, or give the agent a key from the console.
Use the Spiral CLI
- 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
- Create an API key
In the console, under API keys.
- Run Kokoro American English
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/american-english", "input": { "prompt": "" } }'
Then paste one of the prompts above: opencode finds Kokoro American English on Spiral, shows the price and runs it.
Kokoro American English providers and prices
Spiral runs Kokoro American English through fal. Open a card for today's price, with every fee included.
$0.026 per 1,000 characters of prompt. Rounded up to the next 1,000 characters, minimum 1,000.
Settings you can ask for
Kokoro American English works from your prompt. Ask opencode for any of these in your prompt.
| Setting | Allowed values | Default | Description |
|---|---|---|---|
| Voice | af_heart, af_alloy, af_aoede, af_bella, af_jessica, af_kore, af_nicole, af_nova and 12 more | af_heart | Voice ID for the desired voice. |
| Speed | 0.1 to 5 | 1 | Speed of the generated audio. Default is 1.0. |
Every API field of Kokoro TTS · American English is on its tool page: open its card above.
What can you do with Kokoro American English in opencode?
Turn project documentation and release notes into spoken walkthroughs with Kokoro American English. Have the agent prepare narration from the files, then generate manageable passages for review.
Product explainer narration
Turn an approved product explanation into US English speech. Generate each section separately so you can revise individual passages.
Audio editions of articles
Create spoken versions of finished articles, dividing the text into manageable passages for listening and review.
Training lesson narration
Narrate short lesson sections and compare normal delivery with a slower reading before choosing the final audio.
Spoken daily briefings
Convert a prepared daily summary into speech, keeping each topic in its own passage.
Release note summaries
Make an audio summary of product changes after an agent has rewritten the release notes for spoken delivery.
Narration draft reviews
Listen to a script before recording the final production. Compare wording and pacing using the same voice across drafts.
More on Kokoro American English and opencode
Overview
Kokoro American English in other agents
Questions about Kokoro American English in opencode
Can opencode use Kokoro American English?
Yes. Add Spiral to opencode as an MCP server, and opencode can find and run Kokoro American English like any built-in tool.
How much does Kokoro American English cost in opencode?
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 opencode plan is separate.
Do I need a fal account to use Kokoro American English in opencode?
No. Spiral runs Kokoro American English 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 American English in opencode?
About two minutes: add the server, then sign in, then check it.
Does opencode wait while Kokoro American English runs?
Kokoro American English runs in the background. opencode starts the run, checks on it and gives you the audio when it's ready.
What is Kokoro American English useful for?
Use it to turn finished English scripts into spoken explainers, lessons, article narration, or updates. Prepare the wording before generating the speech.
How much text should I generate at once?
The maker recommends roughly 100 to 200 tokens per passage for most voices. Treat that as guidance for individual passages, rather than a maximum length for an entire project.
Why does a long passage sound rushed?
The maker flags rushing above about 400 tokens. Try splitting the passage first, then reduce the speaking speed if needed.
Are the token recommendations word counts?
No. Kokoro processes phonemes, so 100 words should not be treated as 100 model tokens.
What sample rate does Kokoro use?
The maker's reference implementation uses 24 kHz for generated speech. That is the reference audio rate, rather than a promise about every exported file format.
Start using Kokoro American English in opencode
One Spiral account for every tool your agent needs. No subscription; you pay per run.
Paste this into opencode:
set up https://spiral.ai/SKILL.md


