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

Instinct · Audio

How to Use Kotoba STT in Instinct

Kotoba STT turns recorded speech into text, with a focus on Japanese and East Asian languages. Use it for clips up to two minutes when you need a transcript, word timings, or speaker labels.

Prompts to try with Kotoba STT in Instinct

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

Every morning, use Kotoba STT to transcribe new Japanese voice messages of two minutes or less. Preserve each transcript and list any explicit requests separately.

Kotoba STTInstinct
Try asking
  • Each afternoon, use Kotoba STT to transcribe new English product-demo recordings of two minutes or less with word timings. Prepare caption drafts for review.

  • Every weekday, use Kotoba STT to transcribe new Japanese interview excerpts of two minutes or less with speaker labels and timings. Keep each excerpt separate and identify passages worth reviewing.

  • Each evening, use Kotoba STT to transcribe new Korean customer comments of two minutes or less. Put recurring topics in a separate digest with the supporting transcript passages.

  • Every Friday, use Kotoba STT to transcribe new Japanese introduction recordings of two minutes or less with personal names written in katakana. Prepare the transcripts for a name-spelling review.

How to set up Kotoba STT in Instinct

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

Use the Spiral skill

  1. Send Instinct 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 Spiral's MCP server

  1. Create an API key

    In the console, open API keys and create a key for Instinct. Copy it.

  2. Send Instinct this message

    Instinct reads Spiral's skill and asks for your API key.

    set up https://spiral.ai/SKILL.md
  3. Give Instinct the key

    When Instinct asks for the key, add it where Instinct keeps secrets, never in the chat itself.

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 Kotoba STT

    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": "kotoba-technologies/kotoba-stt/v1/speech-to-text",
        "input": {
          "audio_url": "<audio_url>",
          "language": "ja"
        }
      }'

Then paste one of the prompts above: Instinct finds Kotoba STT on Spiral, shows the price and runs it.

Kotoba STT providers and prices

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

falAudio
Kotoba STT · Speech to Text
kotoba-technologies/kotoba-stt/v1/speech-to-text

Settings you can ask for

Kotoba STT works from your audio URL. Ask Instinct for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Languageja, en, ko, zh, es, zh-hk, zh-tw, or auto

Language spoken in the audio.

With timestampson or offoff

Return words with start and end times for each word.

Diarizationon or offoff

Attribute words to speakers (speaker_id on each word; models with speaker tokens only). Word times are null unless with_timestamps is also set.

Kanaon or offoff

Write personal and place names in katakana (Japanese).

Every API field of Kotoba STT · Speech to Text is on its tool page: open its card above.

What can you do with Kotoba STT in Instinct?

Build a recurring review of short recorded messages and interview excerpts. Have the agent preserve each transcript before producing summaries, caption drafts, or lists of follow-up questions.

Japanese interview excerpts

Transcribe an interview excerpt of up to two minutes with speaker labels and timings, then have your agent arrange the transcript for editorial review.

Caption drafts for short videos

Transcribe a video's spoken audio in clips of up to two minutes with word timings. Have your agent turn the timed text into caption drafts for review.

Product demo transcripts

Turn a short narrated demo into text, supplying product names as spelling guidance. Use the transcript as the starting point for written instructions.

Customer research excerpts

Transcribe recorded customer comments in clips of up to two minutes. Keep the transcript beside any themes or observations your agent extracts from it.

Japanese name review

Request katakana personal names in a short Japanese recording to prepare a phonetic transcript for a reviewer.

Recorded voice notes

Transcribe short Japanese, English, Korean, or Chinese voice notes. Have your agent turn the text into a checklist while preserving the original transcript.

Questions about Kotoba STT in Instinct

Can Instinct use Kotoba STT?

Yes. Add Spiral to Instinct as an MCP server, and Instinct can find and run Kotoba STT like any built-in tool.

How much does Kotoba STT cost in Instinct?

Up to $0.005382 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 Instinct plan is separate.

Do I need a fal account to use Kotoba STT in Instinct?

You need no fal account. Instinct uses one Spiral API key for every tool, and Spiral runs Kotoba STT on its own fal account.

How long does it take to set up Kotoba STT in Instinct?

About two minutes: create an API key, then send Instinct this message, then give Instinct the key.

Does Instinct wait while Kotoba STT runs?

Kotoba STT runs in the background. Instinct starts the run, checks on it and gives you the json when it's ready.

What is Kotoba STT best suited for?

Recorded speech, especially Japanese and East Asian audio. Word timings and speaker labels make it useful for preparing caption drafts and reviewing interview excerpts.

How long can a recording be?

Keep each clip within two minutes. For a longer recording, prepare shorter excerpts before transcription.

Which spoken languages are documented?

Kotoba documents Japanese, English, Korean, and Chinese for file transcription.

How can I guide the spelling of names and technical terms?

Supply the relevant spellings as keywords, such as a speaker's name or a product name. Treat them as spelling guidance and check the resulting transcript against the recording.

Can I get speaker labels with timings?

Yes. Request speaker separation and word timings together when you need to see who spoke and where their words occur in the recording.

Get started

Start using Kotoba STT in Instinct

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

Paste this into Instinct:

Set up Instinct

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