# Kotoba STT · Speech to Text

Transcribe audio and video to text with Kotoba STT · Speech to Text from fal through one Spiral API key. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: fal
- Category: Audio
- Runs: In the background
- Returns: json
- Tool id: `fal` / `kotoba-technologies/kotoba-stt/v1/speech-to-text`
- Page: https://spiral.ai/tools/fal/kotoba-technologies/kotoba-stt/v1/speech-to-text

## Pricing

Up to $0.005382 per run at the default inputs for 60 seconds of input.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 30 minutes
- Longest run, end to end: 930 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `audio_url` (required) | URL or file |  | — | Speech to transcribe: an https:// URL on fal's CDN (Playground uploads and microphone recordings) or a base64 data: URI. Up to 2 minutes. |
| `language` (required) | one of | ja, en, ko, zh, es, zh-hk, zh-tw, auto | — | Language spoken in the audio. |
| `with_timestamps` | true or false |  | false | Return `words` with start and end times for each word. |
| `diarization` | true or false |  | false | Attribute words to speakers (`speaker_id` on each word; models with speaker tokens only). Word times are null unless `with_timestamps` is also set. |
| `keywords` | list |  | — | Up to 1000 terms of at most 64 characters, such as names or product words, whose spelling the transcript should prefer. |
| `kana` | true or false |  | false | Write personal and place names in katakana (Japanese). |

## Example

```bash
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"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=fal&model=kotoba-technologies%2Fkotoba-stt%2Fv1%2Fspeech-to-text

## Common questions

### Kotoba STT · Speech to Text

**How much does Kotoba STT · Speech to Text cost?**

Up to $0.005382 per run at the default inputs for 60 seconds of input. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Kotoba STT · Speech to Text through an API?**

Send `POST /v1/runs` with `"provider": "fal"`, `"model": "kotoba-technologies/kotoba-stt/v1/speech-to-text"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with fal to use Kotoba STT · Speech to Text?**

No. Spiral runs it on its own fal account and charges your Spiral balance.

**Can my AI agent use Kotoba STT · Speech to Text?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

