bytedance/seed-asr-2.0

音声からテキスト

Seed ASR 2.0 API by ByteDance

bytedance/seed-asr-2.0

Seed-asr-2.0

BytePlus Seed Speech recording-file recognition (ASR 2.0): transcribe an audio file to text with punctuation, ITN, sentence segmentation, speaker diarization, and 51-language support.

Seed ASR 2.0 は ByteDance が開発したモデルです。Atlas Cloud（運営：Atlas Cloud AI LLC）は本モデルへのアクセスを提供するものであり、その所有者ではありません。すべての商標は各所有者に帰属します。

入力

音声 *

ファイルをドラッグ＆ドロップするか、クリックしてアップロード

MAX:1

フォーマット

言語

数値正規化

句読点を付与

意味の平滑化

話者分離

追加設定

出力

待機中

Ever wondered how to get that flawless glow? Introducing our new skincare line designed for real life.

パラメータ

コード例
import requests
import time

# Step 1: Start audio generation
generate_url = "https://api.atlascloud.ai/api/v1/model/generateAudio"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "bytedance/seed-asr-2.0",  # Required. model name
    "audio_url": "example_value",  # Required. URL of the audio file to transcribe
    "format": "mp3",  # Audio container format. options: mp3 | wav | ogg | raw
    "language": "example_value",  # Optional language code
    "enable_itn": True,  # Inverse text normalization (e
    "enable_punc": False,  # Add punctuation to the transcript
    "enable_ddc": False,  # Semantic smoothing (remove fillers/repeats)
    "enable_speaker_info": False,  # Speaker diarization (<=10 speakers)
    "show_utterances": False,  # Return per-sentence segments with timestamps
    "boosting_table_name": "example_value",  # Hotword table name to boost recognition of listed terms (e
    "correct_table_name": "example_value",  # Correction table name: post-recognition forced replacement (wrong→right pairs)
    "context": "example_value",  # Inline hotwords, no table needed
}

generate_response = requests.post(generate_url, headers=headers, json=data)
generate_result = generate_response.json()
prediction_id = generate_result["data"]["id"]

# Step 2: Poll for result
poll_url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"

def check_status():
    while True:
        response = requests.get(poll_url, headers={"Authorization": "Bearer $ATLASCLOUD_API_KEY"})
        result = response.json()

        if result["data"]["status"] in ["completed", "succeeded"]:
            print("Generated audio:", result["data"]["outputs"][0])
            return result["data"]["outputs"][0]
        elif result["data"]["status"] == "failed":
            raise Exception(result["data"]["error"] or "Generation failed")
        else:
            # Still processing, wait 2 seconds
            time.sleep(2)

audio_url = check_status()

インストール

お使いの言語に必要なパッケージをインストールしてください。

pip install requests

認証

すべての API リクエストには API キーによる認証が必要です。API キーは Atlas Cloud ダッシュボードから取得できます。

export ATLASCLOUD_API_KEY="your-api-key-here"

HTTP ヘッダー

import os

API_KEY = os.environ.get("ATLASCLOUD_API_KEY")
headers = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {API_KEY}"
}

API キーを安全に保管してください

API キーをクライアントサイドのコードや公開リポジトリに公開しないでください。代わりに環境変数またはバックエンドプロキシを使用してください。

リクエストを送信

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateAudio"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}
data = {
    "model": "your-model",
    "text": "Hello, welcome to AtlasCloud text-to-speech."
}

response = requests.post(url, headers=headers, json=data)
print(response.json())

リクエストを送信

非同期生成リクエストを送信します。API は予測 ID を返し、それを使用してステータスの確認や結果の取得ができます。

POST/api/v1/model/generateAudio

リクエストボディ

import requests

url = "https://api.atlascloud.ai/api/v1/model/generateAudio"
headers = {
    "Content-Type": "application/json",
    "Authorization": "Bearer $ATLASCLOUD_API_KEY"
}

data = {
    "model": "bytedance/seed-asr-2.0",
    "text": "Hello, welcome to AtlasCloud text-to-speech."
}

response = requests.post(url, headers=headers, json=data)
result = response.json()

print(f"Prediction ID: {result['data']['id']}")
print(f"Status: {result['data']['status']}")

レスポンス

{
  "code": 200,
  "data": {
    "id": "pred_abc123",
    "status": "processing",
    "model": "model-name",
    "created_at": "2025-01-01T00:00:00Z"
  }
}

ステータスを確認

予測エンドポイントをポーリングして、リクエストの現在のステータスを確認します。

GET/api/v1/model/prediction/{prediction_id}

ポーリング例

import requests
import time

prediction_id = "pred_abc123"
url = f"https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}"
headers = { "Authorization": "Bearer $ATLASCLOUD_API_KEY" }

while True:
    response = requests.get(url, headers=headers)
    result = response.json()
    status = result["data"]["status"]
    print(f"Status: {status}")

    if status in ["completed", "succeeded"]:
        output_url = result["data"]["outputs"][0]
        print(f"Output URL: {output_url}")
        break
    elif status == "failed":
        print(f"Error: {result['data'].get('error', 'Unknown')}")
        break

    time.sleep(3)

ステータス値

processingリクエストはまだ処理中です。

completed生成が完了しました。出力が利用可能です。

succeeded生成が成功しました。出力が利用可能です。

failed生成に失敗しました。エラーフィールドを確認してください。

完了レスポンス

{
  "data": {
    "id": "pred_abc123",
    "status": "completed",
    "outputs": [
      "https://storage.atlascloud.ai/outputs/result.mp3"
    ],
    "metrics": {
      "predict_time": 8.3
    },
    "created_at": "2025-01-01T00:00:00Z",
    "completed_at": "2025-01-01T00:00:10Z"
  }
}

入力 Schema

以下のパラメータがリクエストボディで使用できます。

合計: 12必須: 2任意: 10

modelstringrequired

model name

Default: "bytedance/seed-asr-2.0"

audio_urlstringrequired

URL of the audio file to transcribe. Public URL or Base64. Formats: wav/mp3/ogg/raw. Max ~512MB.

formatstring

Audio container format.

Default: "mp3"

mp3wavoggraw

languagestring

Optional language code. Leave empty to auto-recognize Chinese/English/dialects. Or set a code, e.g. en-US, zh-CN, yue-CN, ja-JP, es-MX (51 languages supported).

enable_itnboolean

Inverse text normalization (e.g. 'one hundred' -> '100').

Default: true

enable_puncboolean

Add punctuation to the transcript.

Default: false

enable_ddcboolean

Semantic smoothing (remove fillers/repeats).

Default: false

enable_speaker_infoboolean

Speaker diarization (<=10 speakers).

Default: false

show_utterancesboolean

Return per-sentence segments with timestamps.

Default: false

boosting_table_namestring

Hotword table name to boost recognition of listed terms (e.g. product names). Tables are provisioned server-side by Atlas — contact us with your word list to get a table name. NOTE: a nonexistent table name is silently ignored (the task still succeeds).

correct_table_namestring

Correction table name: post-recognition forced replacement (wrong→right pairs). Provisioned server-side by Atlas, same as boosting_table_name. A nonexistent table name is silently ignored.

contextstring

Inline hotwords, no table needed. Must be a JSON STRING of the form {"hotwords":[{"word":"YourTerm"}]}. WARNING: plain non-JSON text makes the task FAIL; unrecognized JSON keys are silently ignored.

リクエストボディの例

{
  "model": "bytedance/seed-asr-2.0",
  "audio_url": "example_audio_url",
  "format": "mp3",
  "enable_itn": true,
  "enable_punc": false,
  "enable_ddc": false,
  "enable_speaker_info": false,
  "show_utterances": false
}

出力 Schema

API は生成された出力 URL を含む予測レスポンスを返します。

modelstring

model name

Default: "bytedance/seed-asr-2.0"

created_atstring

ISO timestamp of when the request was created.

idstring

Unique identifier for the prediction.

outputsarray

Array with the recognized transcript text (outputs[0]).

statusstring

Status: created, processing, completed, or failed.

stt_resultobject

Structured transcription result: text, duration (seconds), and words[] with per-word timestamps when show_utterances=true.

レスポンス例

{
  "id": "pred_abc123",
  "status": "completed",
  "model": "model-name",
  "outputs": [
    "https://storage.atlascloud.ai/outputs/result.png"
  ],
  "metrics": {
    "predict_time": 8.3
  },
  "created_at": "2025-01-01T00:00:00Z",
  "completed_at": "2025-01-01T00:00:10Z"
}

Atlas Cloud Skills

Atlas Cloud Skills は 400 以上の AI モデルを AI コーディングアシスタントに直接統合します。ワンコマンドでインストールし、自然言語で画像・動画生成や LLM との対話が可能です。

対応クライアント

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 対応クライアント

インストール

npx skills add AtlasCloudAI/atlas-cloud-skills

API キーの設定

Atlas Cloud ダッシュボードから API キーを取得し、環境変数として設定してください。

export ATLASCLOUD_API_KEY="your-api-key-here"

機能

インストール後、AI アシスタントで自然言語を使用してすべての Atlas Cloud モデルにアクセスできます。

画像生成Nano Banana 2、Z-Image などのモデルで画像を生成します。

動画作成Kling、Vidu、Veo などでテキストや画像から動画を作成します。

LLM チャットQwen、DeepSeek などの大規模言語モデルと対話します。

メディアアップロード画像編集や画像から動画へのワークフロー用にローカルファイルをアップロードします。

詳細を見る

github.com/AtlasCloudAI/atlas-cloud-skills

MCP Server

Atlas Cloud MCP Server は Model Context Protocol を通じて IDE と 400 以上の AI モデルを接続します。MCP 対応のあらゆるクライアントで動作します。

対応クライアント

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 対応クライアント

インストール

npx -y atlascloud-mcp

設定

以下の設定を IDE の MCP 設定ファイルに追加してください。

{
  "mcpServers": {
    "atlascloud": {
      "command": "npx",
      "args": [
        "-y",
        "atlascloud-mcp"
      ],
      "env": {
        "ATLASCLOUD_API_KEY": "your-api-key-here"
      }
    }
  }
}

利用可能なツール

atlas_generate_imageテキストプロンプトから画像を生成します。

atlas_generate_videoテキストや画像から動画を作成します。

atlas_chat大規模言語モデルと対話します。

atlas_list_models400 以上の利用可能な AI モデルを閲覧します。

atlas_quick_generate最適なモデルを自動選択し、ワンステップでコンテンツを作成。

atlas_upload_mediaAPI ワークフロー用にローカルファイルをアップロードします。

詳細を見る

github.com/AtlasCloudAI/mcp-server

APIスキーマ

{
  "info": {
    "description": "The AtlasCloud API.",
    "title": "AtlasCloud API",
    "version": "1.0.0"
  },
  "paths": {
    "/api/v1/model/generateAudio": {
      "post": {
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "The request status."
          }
        },
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/Input"
              }
            }
          }
        }
      },
      "x-api-name": "model_run"
    },
    "/api/v1/model/prediction/{request_id}": {
      "get": {
        "responses": {
          "200": {
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/PredictionResponse"
                }
              }
            },
            "description": "Result of the request."
          }
        },
        "parameters": [
          {
            "in": "path",
            "name": "request_id",
            "schema": {
              "type": "string",
              "description": "Request ID"
            },
            "required": true
          }
        ]
      },
      "x-api-name": "model_result"
    }
  },
  "openapi": "3.0.0",
  "servers": [
    {
      "url": "https://api.atlascloud.ai"
    }
  ],
  "components": {
    "schemas": {
      "Input": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "bytedance/seed-asr-2.0"
          },
          "audio_url": {
            "description": "URL of the audio file to transcribe. Public URL or Base64. Formats: wav/mp3/ogg/raw. Max ~512MB.",
            "type": "string",
            "x-ui-component": "uploaders"
          },
          "format": {
            "type": "string",
            "description": "Audio container format.",
            "default": "mp3",
            "enum": [
              "mp3",
              "wav",
              "ogg",
              "raw"
            ]
          },
          "language": {
            "description": "Optional language code. Leave empty to auto-recognize Chinese/English/dialects. Or set a code, e.g. en-US, zh-CN, yue-CN, ja-JP, es-MX (51 languages supported).",
            "type": "string"
          },
          "enable_itn": {
            "type": "boolean",
            "description": "Inverse text normalization (e.g. 'one hundred' -> '100').",
            "default": true
          },
          "enable_punc": {
            "type": "boolean",
            "description": "Add punctuation to the transcript.",
            "default": false
          },
          "enable_ddc": {
            "type": "boolean",
            "description": "Semantic smoothing (remove fillers/repeats).",
            "default": false
          },
          "enable_speaker_info": {
            "type": "boolean",
            "description": "Speaker diarization (<=10 speakers).",
            "default": false
          },
          "show_utterances": {
            "type": "boolean",
            "description": "Return per-sentence segments with timestamps.",
            "default": false
          },
          "boosting_table_name": {
            "type": "string",
            "description": "Hotword table name to boost recognition of listed terms (e.g. product names). Tables are provisioned server-side by Atlas — contact us with your word list to get a table name. NOTE: a nonexistent table name is silently ignored (the task still succeeds)."
          },
          "correct_table_name": {
            "type": "string",
            "description": "Correction table name: post-recognition forced replacement (wrong→right pairs). Provisioned server-side by Atlas, same as boosting_table_name. A nonexistent table name is silently ignored."
          },
          "context": {
            "type": "string",
            "description": "Inline hotwords, no table needed. Must be a JSON STRING of the form {\"hotwords\":[{\"word\":\"YourTerm\"}]}. WARNING: plain non-JSON text makes the task FAIL; unrecognized JSON keys are silently ignored."
          }
        },
        "required": [
          "model",
          "audio_url"
        ],
        "type": "object",
        "x-order-properties": [
          "model",
          "audio_url",
          "format",
          "language",
          "enable_itn",
          "enable_punc",
          "enable_ddc",
          "enable_speaker_info",
          "show_utterances",
          "context",
          "boosting_table_name",
          "correct_table_name"
        ]
      },
      "PredictionResponse": {
        "properties": {
          "model": {
            "type": "string",
            "description": "model name",
            "default": "bytedance/seed-asr-2.0"
          },
          "created_at": {
            "description": "ISO timestamp of when the request was created.",
            "format": "date-time",
            "type": "string"
          },
          "id": {
            "description": "Unique identifier for the prediction.",
            "type": "string"
          },
          "outputs": {
            "description": "Array with the recognized transcript text (outputs[0]).",
            "items": {
              "type": "string"
            },
            "type": "array"
          },
          "status": {
            "description": "Status: created, processing, completed, or failed.",
            "type": "string"
          },
          "urls": {
            "description": "Object containing related API endpoints.",
            "type": "object"
          },
          "stt_result": {
            "type": "object",
            "description": "Structured transcription result: text, duration (seconds), and words[] with per-word timestamps when show_utterances=true.",
            "properties": {
              "text": {
                "type": "string",
                "description": "Full transcript."
              },
              "duration": {
                "type": "number",
                "description": "Audio duration in seconds."
              },
              "words": {
                "type": "array",
                "description": "Word-level segments (show_utterances=true). Times in seconds.",
                "items": {
                  "type": "object",
                  "properties": {
                    "text": {
                      "type": "string"
                    },
                    "start": {
                      "type": "number"
                    },
                    "end": {
                      "type": "number"
                    },
                    "type": {
                      "type": "string",
                      "description": "word | utterance"
                    },
                    "speaker_id": {
                      "type": "string",
                      "description": "Present when enable_speaker_info=true."
                    }
                  }
                }
              }
            }
          }
        },
        "type": "object"
      }
    },
    "securitySchemes": {
      "apiKeyAuth": {
        "in": "header",
        "name": "Authorization",
        "type": "apiKey"
      }
    }
  }
}

LLMフレンドリーなプロンプトテンプレート

# bytedance/seed-asr-2.0

> BytePlus Seed Speech recording-file recognition (ASR 2.0): transcribe an audio file to text with punctuation, ITN, sentence segmentation, speaker diarization, and 51-language support.


## Overview

- **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateAudio` — start an async generation; returns a `prediction_id`
- **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes
- **Model ID**: `bytedance/seed-asr-2.0`


## API Information

This model can be used via our HTTP API or more conveniently via our client libraries.
See the input and output schema below, as well as the usage examples.


### Input Schema

The API accepts the following input parameters:

- **`model`** (`string`, _required_):
  model name
  - Default: `"bytedance/seed-asr-2.0"`

- **`audio_url`** (`string`, _required_):
  URL of the audio file to transcribe. Public URL or Base64. Formats: wav/mp3/ogg/raw. Max ~512MB.

- **`format`** (`string`, _optional_):
  Audio container format.
  - Default: `"mp3"`
  - Options: "mp3", "wav", "ogg", "raw"

- **`language`** (`string`, _optional_):
  Optional language code. Leave empty to auto-recognize Chinese/English/dialects. Or set a code, e.g. en-US, zh-CN, yue-CN, ja-JP, es-MX (51 languages supported).

- **`enable_itn`** (`boolean`, _optional_):
  Inverse text normalization (e.g. 'one hundred' -> '100').
  - Default: `true`

- **`enable_punc`** (`boolean`, _optional_):
  Add punctuation to the transcript.
  - Default: `false`

- **`enable_ddc`** (`boolean`, _optional_):
  Semantic smoothing (remove fillers/repeats).
  - Default: `false`

- **`enable_speaker_info`** (`boolean`, _optional_):
  Speaker diarization (<=10 speakers).
  - Default: `false`

- **`show_utterances`** (`boolean`, _optional_):
  Return per-sentence segments with timestamps.
  - Default: `false`

- **`context`** (`string`, _optional_):
  Inline hotwords, no table needed. Must be a JSON STRING of the form {"hotwords":[{"word":"YourTerm"}]}. WARNING: plain non-JSON text makes the task FAIL; unrecognized JSON keys are silently ignored.

- **`boosting_table_name`** (`string`, _optional_):
  Hotword table name to boost recognition of listed terms (e.g. product names). Tables are provisioned server-side by Atlas — contact us with your word list to get a table name. NOTE: a nonexistent table name is silently ignored (the task still succeeds).

- **`correct_table_name`** (`string`, _optional_):
  Correction table name: post-recognition forced replacement (wrong→right pairs). Provisioned server-side by Atlas, same as boosting_table_name. A nonexistent table name is silently ignored.



**Required Parameters Example**:

```json
{
  "model": "bytedance/seed-asr-2.0",
  "audio_url": ""
}
```


**Full Example**:

```json
{
  "model": "bytedance/seed-asr-2.0",
  "audio_url": "",
  "format": "mp3",
  "language": "",
  "enable_itn": true,
  "enable_punc": false,
  "enable_ddc": false,
  "enable_speaker_info": false,
  "show_utterances": false,
  "context": "",
  "boosting_table_name": "",
  "correct_table_name": ""
}
```


### Output Schema

The API returns the following output format:


- **`model`** (`string`, _optional_):
  model name
  - Default: `"bytedance/seed-asr-2.0"`

- **`created_at`** (`string`, _optional_):
  ISO timestamp of when the request was created.

- **`id`** (`string`, _optional_):
  Unique identifier for the prediction.

- **`outputs`** (`array[string]`, _optional_):
  Array with the recognized transcript text (outputs[0]).

- **`status`** (`string`, _optional_):
  Status: created, processing, completed, or failed.

- **`urls`** (`object`, _optional_):
  Object containing related API endpoints.

- **`stt_result`** (`object`, _optional_):
  Structured transcription result: text, duration (seconds), and words[] with per-word timestamps when show_utterances=true.
  - Properties:
    - **`text`** (`string`, _optional_):
      Full transcript.

    - **`duration`** (`number`, _optional_):
      Audio duration in seconds.

    - **`words`** (`array[object]`, _optional_):
      Word-level segments (show_utterances=true). Times in seconds.
      - Item properties:
        - **`text`** (`string`, _optional_):

        - **`start`** (`number`, _optional_):

        - **`end`** (`number`, _optional_):

        - **`type`** (`string`, _optional_):
          word | utterance

        - **`speaker_id`** (`string`, _optional_):
          Present when enable_speaker_info=true.





**Example Response**:

```json
{
  "model": "bytedance/seed-asr-2.0",
  "created_at": "",
  "id": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {},
  "stt_result": {
    "text": "",
    "duration": 0,
    "words": [
      {
        "text": "",
        "start": 0,
        "end": 0,
        "type": "",
        "speaker_id": ""
      }
    ]
  }
}
```


## Usage Examples

### cURL

```bash
# Step 1: Start generation (async)
curl -X POST "https://api.atlascloud.ai/api/v1/model/generateAudio" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bytedance/seed-asr-2.0",
  "audio_url": "",
  "format": "mp3",
  "language": "",
  "enable_itn": true,
  "enable_punc": false,
  "enable_ddc": false,
  "enable_speaker_info": false,
  "show_utterances": false,
  "context": "",
  "boosting_table_name": "",
  "correct_table_name": ""
}'

# Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}}

# Step 2: Poll for result (replace {prediction_id} with the id returned above)
curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \
  -H "Authorization: Bearer $ATLASCLOUD_API_KEY"

# Keep polling until status is "completed", "succeeded" or "failed"
# When completed, outputs will contain the generated content URL(s)
```

## Additional Resources

### Documentation

- [Model Playground](https://www.atlascloud.ai/models/bytedance/seed-asr-2.0)

Ever wondered how to get that flawless glow? Introducing our new skincare line designed for real life.

読み込み中...

Seed ASR 2.0 (Recording-File Recognition)

Transcribe an audio file to text with punctuation, ITN, sentence segmentation, speaker diarization, and 51-language support.

🌟 Key Features

🗣 High-Accuracy Transcription

State-of-the-art recognition tuned for real-world recordings.

🌍 51 Languages

Auto-detects Chinese/English/dialects, or pin a language code.

🎯 Rich Output

Punctuation, inverse text normalization, per-word timestamps, speaker labels.

📻 Far-Field Optimized

Robust to meeting-room and call-center audio.

⚙️ Parameters

Parameter	Required	Description
`audio_url`*	✅	Audio file URL or Base64. Formats: wav/mp3/ogg/raw.
`format`	⬜	Audio format: `mp3` (default) / `wav` / `ogg` / `raw`.
`language`	⬜	Language code (e.g. `en-US`, `yue-CN`); empty = auto (CN/EN/dialects). 51 languages.
`enable_itn`	⬜	Inverse text normalization. Default `true`.
`enable_punc`	⬜	Add punctuation. Default `false`.
`enable_ddc`	⬜	Semantic smoothing. Default `false`.
`enable_speaker_info`	⬜	Speaker diarization. Default `false`.
`show_utterances`	⬜	Per-word timestamps in `stt_result.words`. Default `false`.
`context`	⬜	Inline hotwords — no table needed. JSON string: `{"hotwords":[{"word":"YourTerm"}]}`. See below.
`boosting_table_name`	⬜	Server-side hotword table name (provisioned by Atlas).
`correct_table_name`	⬜	Server-side correction table name (wrong→right replacement, provisioned by Atlas).

🔥 Hotwords & Correction

Two ways to improve recognition of product names, people, and domain terms:

1. Inline via context (recommended — self-service, per request):

{
  "audio_url": "https://…/meeting.mp3",
  "context": "{\"hotwords\":[{\"word\":\"Zylophex\"},{\"word\":\"AtlasCloud\"}]}"
}

⚠️ context must be a JSON string exactly as above. Plain text (non-JSON) makes the task fail; unrecognized JSON keys are silently ignored.

2. Server-side tables via boosting_table_name / correct_table_name: for large or stable word lists. Tables live in the service account — send Atlas your word list and we provision the table and hand back its name. ⚠️ A nonexistent table name is silently ignored (the task still succeeds), so use the exact name we give you.

📤 Output

outputs[0] contains the recognized transcript text. stt_result carries the structured result: text, duration (seconds), and — with show_utterances=true — words[] with per-word start/end timestamps in seconds (plus speaker_id when diarization is on).

🎯 Use Cases

Meeting & Interview Transcription — turn recordings into searchable text.
Media Subtitling — transcribe podcasts/videos with timestamps.
Voice Analytics — call-center QA, speaker diarization.
Multilingual Content — transcribe across 51 languages.

類似モデルを探索

NEW

テキストから音声

Seed Audio 1.0

Doubao‑Audio‑Generate‑1.0 is Doubao Voice’s next‑generation audio‑generation engine. The industry‑first commercial tool creates film‑grade audio with just one prompt. It eliminates cumbersome audio‑engineering work. Creators generate publish‑ready radio dramas, podcasts and branded audio easily, shifting from a simple voice‑generator to an AI audio director. It serves audiobooks, serialized episodes and commercial audio for high‑quality narrative‑driven production.

MiniMax Music 3.0

MiniMax Music 3.0 is MiniMax's 11.1B-parameter open-weights music model that turns a musical description and optional lyrics into a complete, fully arranged and mixed song of up to five minutes - vocals, instrumentation and production included - in a single generation, with section-tag control over the arrangement and vocal or instrumental output.

MiniMax Lyrics Generation

MiniMax Lyrics Generation is a dedicated lyric-writing model that turns a one-line theme into a complete, professionally structured set of song lyrics - title, style tags, and sections marked with [Verse]/[Chorus] structure tags - and can also edit, continue, or restructure existing lyrics, with output directly usable as the lyrics input of MiniMax's music models.

Suno chirp-v4-5-all

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-v4-5-plus

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-auk

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-fenix

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-v3-5

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-v4

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

Suno chirp-v5

Suno text-to-music via APIMart: inspiration mode (custom=false) turns a description into a song; custom mode (custom=true) uses your own lyrics. Async; returns 2 tracks per generation.

xAI TTS v1

xAI TTS v1 is a high-fidelity text-to-speech model that converts text into natural, expressive speech with sub-second latency, supporting 20 languages and 80+ voices with fine-grained delivery control.

From

$0.015/K文字

テキストから音声

MiniMax Music 2.6

MiniMax text-to-music (latest): generate a full vocal or instrumental song from a style prompt plus lyrics with [Verse]/[Chorus] structure tags. Synchronous single-call generation.

ElevenLabs v3 Text-to-Speech

ElevenLabs v3 Text-to-Speech model. High-quality speech generation from text prompts.

xAI STT v1

xAI STT v1 is a production-grade speech-to-text model that transcribes audio into accurate, formatted text. It supports 24+ languages with automatic language detection, word-level timestamps, speaker diarization, multichannel transcription, and inverse text normalization.

From

$0.002/分

ひとつのAPIで、あらゆるメディアAIを。

すべてのモデルを探索