# Kotoba Speech-to-Text API

> 最長 2 分鐘片段的語音轉文字，針對日文最佳化，支援單字時間戳記和關鍵字提示

從 `audio_url` 轉錄最長 2 分鐘的音訊片段。將 `language` 設為 ja、en、ko、zh、es、zh-hk、zh-tw 或 auto。選用的 `with_timestamps` 會回傳每個單字的開始和結束時間，`diarization` 會標記說話者，`keywords` 接受最多 1000 個詞語以偏向特定拼寫，而 `kana` 會在日文中以片假名書寫名稱。輸出包含文字、偵測到的語言和音訊時長。

- Model id: `kotoba-technologies/kotoba-stt/v1/speech-to-text`
- Made by: Kotoba Technologies
- Category: Speech to Text
- Output: text
- Price per second of your input audio: $0.0000694 / second of input audio (cheapest run $0.001 (1 API credit))
- Run: `POST https://api.doitong.ru/v1/run/kotoba-technologies/kotoba-stt/v1/speech-to-text`
- Quote: `POST https://api.doitong.ru/v1/quote/kotoba-technologies/kotoba-stt/v1/speech-to-text`
- Docs page: https://doitong.com/zh-TW/developers/models/kotoba-technologies/kotoba-stt/v1/speech-to-text

## Pricing

Price: **$0.0000694 / second of input audio**. Price per second of your input audio: the input files are measured before the run (length, resolution, frame rate). The quote measures the same files and is exactly what the run charges.

The full example input below costs $0.001 = 1 API credit (10 s input audio × $0.000069).

Prices are the upstream price in USD, paid from the API balance in API credits (1000 API credits = 1 USD). `POST https://api.doitong.ru/v1/quote/kotoba-technologies/kotoba-stt/v1/speech-to-text` with the same JSON body returns the exact price for that input; the quote is exactly what a run charges. Invalid input is never charged and failed or canceled requests are refunded automatically.

## Input parameters

Send either the canonical name or the native field name (not both). Canonical names are the same across models.

| Parameter | Canonical name | Type | Required | Default | Allowed values / range | Description |
|---|---|---|---|---|---|---|
| `audio_url` | `audio` | string (audio URL) | yes |  |  | 音訊長度限制為 2 分鐘。 |
| `language` |  | enum (string) | yes |  | `ja`, `en`, `ko`, `zh`, `es`, `zh-hk`, `zh-tw`, `auto` | 音訊說話者使用的語言。 |
| `with_timestamps` |  | boolean | no | `false` |  | `words` 中的逐字計時輸出，包括每個單字的開始和結束時間。 |
| `diarization` |  | boolean | no | `false` |  | 逐字層級的說話者歸屬，僅適用於支援說話者 Token 的模型。每個單字都會取得 `speaker_id`，但除非同時啟用 `with_timestamps`，否則其時間會保持為 null。 |
| `keywords` |  | array of string \| null | no |  | ≤ 1000 items | 希望在轉錄文字中優先採用的拼寫，包括名稱或產品術語。最多接受 1000 個詞，每個詞限制為 64 個字元。 |
| `kana` |  | boolean | no | `false` |  | 日文中的人名和地名之片假名寫法。 |

File parameters (`audio`) take a public `https://` URL, a `data:` URI up to 10 MB, or the `file_url` of an upload from `POST /files`.

## Example input

Required parameters only:

```json
{
  "audio": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "language": "ja"
}
```

A fuller example:

```json
{
  "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
  "language": "ja"
}
```

## Run it

Set `DOITONG_API_KEY` to a key from https://doitong.com/developers/dashboard#keys. `?wait=20` returns the finished request in the same call when it is ready within 20 seconds; otherwise poll `GET /requests/{id}` (it also accepts `?wait=`), or pass `webhook_url`.

### curl

```bash
# Run the model; wait up to 20 s for the finished result in the same call
curl -X POST "https://api.doitong.ru/v1/run/kotoba-technologies/kotoba-stt/v1/speech-to-text?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "language": "ja"
  }'

# Still "queued" or "running"? Poll with the id from the response:
curl "https://api.doitong.ru/v1/requests/REQUEST_ID?wait=20" \
  -H "Authorization: Bearer $DOITONG_API_KEY"
```

### JavaScript

```javascript
const API = "https://api.doitong.ru/v1";
const headers = {
  "Authorization": "Bearer " + process.env.DOITONG_API_KEY,
  "Content-Type": "application/json",
};

// Run the model; wait up to 20 s for the finished result in the same call
let res = await fetch(API + "/run/kotoba-technologies/kotoba-stt/v1/speech-to-text?wait=20", {
  method: "POST",
  headers,
  body: JSON.stringify({
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "language": "ja"
  }),
});
let request = await res.json();
if (!res.ok) throw new Error(request.error.code + ": " + request.error.message);

// Not finished yet: long-poll until it is
while (request.status === "queued" || request.status === "running") {
  res = await fetch(API + "/requests/" + request.id + "?wait=20", { headers });
  request = await res.json();
}
if (request.status !== "succeeded") throw new Error(JSON.stringify(request.error));
console.log(request.outputs.map((o) => o.url), request.cost.credits + " API credits ($" + request.cost.usd + ")");
```

### Python

```python
import os
import requests

API = "https://api.doitong.ru/v1"
headers = {"Authorization": "Bearer " + os.environ["DOITONG_API_KEY"]}

payload = {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "language": "ja",
}

# Run the model; wait up to 20 s for the finished result in the same call
r = requests.post(API + "/run/kotoba-technologies/kotoba-stt/v1/speech-to-text", params={"wait": 20}, json=payload, headers=headers)
request = r.json()
if not r.ok:
    raise RuntimeError(request["error"]["code"] + ": " + request["error"]["message"])

# Not finished yet: long-poll until it is
while request["status"] in ("queued", "running"):
    request = requests.get(API + "/requests/" + request["id"], params={"wait": 20}, headers=headers).json()
if request["status"] != "succeeded":
    raise RuntimeError(request["error"])
print([o["url"] for o in request["outputs"]], request["cost"]["credits"], "API credits", "$" + request["cost"]["usd"])
```

### MCP

The MCP server at `https://api.doitong.ru/v1/mcp` exposes the tools `search_models`, `get_model`, `quote`, `run`, `get_request`, `cancel_request`, `list_requests`, `create_upload` and `get_account`. A `run` call for this model:

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "run",
    "arguments": {
      "model_id": "kotoba-technologies/kotoba-stt/v1/speech-to-text",
      "input": {
        "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
        "language": "ja"
      },
      "wait_seconds": 20
    }
  }
}
```

## Response

Every call returns a request object. `status` is one of `queued`, `running`, `succeeded`, `failed`, `canceled`. `outputs` lists the generated files with URLs on our storage (kept forever, or 7 days with `?storage=temporary`; `storage` says which); `output` is the model's own result object with the same URLs.

```json
{
  "id": "req_8k2m4q7x1z9c3v5b6n0p2r4t",
  "object": "request",
  "model": "kotoba-technologies/kotoba-stt/v1/speech-to-text",
  "status": "succeeded",
  "created_at": "2026-10-20T12:00:00Z",
  "started_at": "2026-10-20T12:00:02Z",
  "completed_at": "2026-10-20T12:00:09Z",
  "queue_position": null,
  "cost": {
    "credits": 1,
    "usd": "0.001",
    "charged": 1,
    "refunded": 0
  },
  "input": {
    "audio_url": "https://content.doitong.com/audio/showcase/v3/tools/dub_es.mp3",
    "language": "ja"
  },
  "output": {
    "audio_duration_secs": 1.0,
    "language_code": "string",
    "language_probability": 1.0,
    "text": "string",
    "words": [
      {
        "end": 1.0,
        "speaker_id": "string",
        "start": 1.0,
        "text": "string",
        "type": "word"
      }
    ]
  },
  "outputs": [
    {
      "type": "file",
      "url": "https://content.doitong.com/dev-api/2026/10/20/req_8k2m4q7x1z9c3v5b6n0p2r4t/0-output.jpeg",
      "content_type": "image/jpeg",
      "file_size": 1843200,
      "stored": true
    }
  ],
  "error": null,
  "metrics": {
    "inference_seconds": 6.8
  },
  "urls": {
    "self": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t",
    "cancel": "https://api.doitong.ru/v1/requests/req_8k2m4q7x1z9c3v5b6n0p2r4t/cancel"
  }
}
```

### Output fields (`output`)

| Field | Type | Description |
|---|---|---|
| `audio_duration_secs` | number \| null |  |
| `language_code` | string |  |
| `language_probability` | number |  |
| `text` | string |  |
| `words` | array of object {end, speaker_id, start, text, type} |  |

## Related models

- [Cohere Transcribe](https://doitong.com/developers/models/cohere-transcribe.md) (`cohere-transcribe`): $0.0000694 / second of input audio
- [Elevenlabs - Forced Alignment](https://doitong.com/developers/models/elevenlabs/forced-alignment.md) (`elevenlabs/forced-alignment`): $0.22 / hour of input audio
- [ElevenLabs Speech to Text](https://doitong.com/developers/models/elevenlabs/speech-to-text.md) (`elevenlabs/speech-to-text`): $0.03 / minute of input audio
- [ElevenLabs Speech to Text - Scribe V2](https://doitong.com/developers/models/elevenlabs/speech-to-text/scribe-v2.md) (`elevenlabs/speech-to-text/scribe-v2`): $0.008 / minute of input audio
- [Nemotron 3 Nano Omni · Audio](https://doitong.com/developers/models/nvidia/nemotron-3-nano-omni/audio.md) (`nvidia/nemotron-3-nano-omni/audio`): $0.01 / 1000 tokens
- [Nemotron Asr Multilingual](https://doitong.com/developers/models/nvidia/nemotron-asr-multilingual/asr.md) (`nvidia/nemotron-asr-multilingual/asr`): $0.008 / minute of input audio
- [Pipecat's Smart Turn model](https://doitong.com/developers/models/smart-turn.md) (`smart-turn`): $0.00111 / second of processing time
- [Silero VAD](https://doitong.com/developers/models/silero-vad.md) (`silero-vad`): $0.00001 / second of input audio

## Links

- HTML page: https://doitong.com/developers/models/kotoba-technologies/kotoba-stt/v1/speech-to-text
- All models and guides for AI agents: https://doitong.com/developers/llms.txt
- OpenAPI 3.1 with this model's typed request body: https://doitong.com/developers/openapi.json?model=kotoba-technologies/kotoba-stt/v1/speech-to-text
- Errors: https://doitong.com/developers/docs/errors
- Model details as JSON: https://api.doitong.ru/v1/models/kotoba-technologies/kotoba-stt/v1/speech-to-text