bytedance/seed-asr-2.0

音频转文字

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.

输入

Audio url *

可拖拽文件至此，或点击上传

MAX:1

Format

语言

Enable itn

Enable punc

Enable ddc

Enable speaker info

Show utterances

输出

空闲

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

参数

代码示例
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
}

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()

安装

安装所需的依赖包。

pip install requests

认证

所有 API 请求需要通过 API Key 进行认证。您可以在 Atlas Cloud 控制台获取 API Key。

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

HTTP 请求头

import os

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

保护好您的 API Key

切勿在客户端代码或公开仓库中暴露您的 API Key。请使用环境变量或后端代理。

提交请求

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())

提交请求

提交一个异步生成请求。API 返回一个 prediction ID，您可以用它来检查状态和获取结果。

POST/api/v1/model/generateAudio

请求体

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']}")

响应

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

检查状态

轮询 prediction 端点以检查请求的当前状态。

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

轮询示例

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)

状态值

processing请求仍在处理中。

completed生成完成，输出可用。

succeeded生成成功，输出可用。

failed生成失败，请检查 error 字段。

完成响应

{
  "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"
  }
}

Input Schema

以下参数在请求体中被接受。

总计: 9必填: 2可选: 7

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

请求体示例

{
  "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
}

Output Schema

API 返回包含生成输出 URL 的 prediction 响应。

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.

响应示例

{
  "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 将 400+ AI 模型直接集成到您的 AI 编程助手中。一条命令安装，即可用自然语言生成图像、视频和与 LLM 对话。

支持的客户端

Claude Code

OpenAI Codex

Gemini CLI

Cursor

Windsurf

VS Code

Trae

GitHub Copilot

Cline

Roo Code

Amp

Goose

Replit

40+ 支持的客户端

安装

npx skills add AtlasCloudAI/atlas-cloud-skills

设置 API Key

从 Atlas Cloud 控制台获取 API Key，并将其设置为环境变量。

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

功能

安装后，您可以在 AI 助手中使用自然语言访问所有 Atlas Cloud 模型。

图像生成使用 Nano Banana 2、Z-Image 等模型生成图像。

视频创作使用 Kling、Vidu、Veo 等模型从文本或图像创建视频。

LLM 对话与 Qwen、DeepSeek 等大语言模型对话。

媒体上传上传本地文件用于图像编辑和图生视频工作流。

MCP Server

Atlas Cloud MCP Server 通过 Model Context Protocol 将您的 IDE 与 400+ AI 模型连接。支持任何兼容 MCP 的客户端。

支持的客户端

Cursor

VS Code

Windsurf

Claude Code

OpenAI Codex

Gemini CLI

Cline

Roo Code

100+ 支持的客户端

安装

npx -y atlascloud-mcp

配置

将以下配置添加到您的 IDE 的 MCP 设置文件中。

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

可用工具

atlas_generate_image从文本提示生成图像。

atlas_generate_video从文本或图像创建视频。

atlas_chat与大语言模型对话。

atlas_list_models浏览 400+ 可用 AI 模型。

atlas_quick_generate一步式内容创建，自动选择最佳模型。

atlas_upload_media上传本地文件用于 API 工作流。

了解更多

github.com/AtlasCloudAI/mcp-server

API Schema

{
  "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
          }
        },
        "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"
        ]
      },
      "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"
          }
        },
        "type": "object"
      }
    },
    "securitySchemes": {
      "apiKeyAuth": {
        "in": "header",
        "name": "Authorization",
        "type": "apiKey"
      }
    }
  }
}

LLM 友好的提示词模板

# 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`



**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
}
```


### 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.



**Example Response**:

```json
{
  "model": "bytedance/seed-asr-2.0",
  "created_at": "",
  "id": "",
  "outputs": [
    ""
  ],
  "status": "",
  "urls": {}
}
```


## 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
}'

# 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.

加载中...

Seed ASR 2.0 (Recording-File Recognition)

Seed ASR 2.0 (BytePlus Seed Speech) transcribes an audio file into text. Built on an audio-conditioned LLM, it delivers state-of-the-art accuracy with punctuation, inverse text normalization, sentence segmentation and speaker diarization.

🌟 Key Features

🗣 High-Accuracy Transcription

LLM-based recognition with deep context understanding — strong on dynamic, real-world speech.

🌍 51 Languages

Chinese, English and domestic dialects (Cantonese, Shanghainese, Sichuanese, etc.) plus 48 more including Japanese, Spanish, Portuguese, Arabic, Hindi.

🎯 Rich Output

Punctuation, ITN (number normalization), semantic smoothing, per-sentence timestamps, and speaker diarization (up to 10 speakers).

📻 Far-Field Optimized

~50% error-rate reduction on far-field test sets (speakers, TVs, glasses).

⚙️ 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-sentence segments + timestamps. Default `false`.

📤 Output

outputs[0] contains the recognized transcript text.

🎯 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.

探索类似模型

NEW

文字转音频

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.

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.

ElevenLabs v3 Text-to-Speech

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

Suno chirp-auk

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-fenix

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v3-0

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v3-5

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v3-5-tau

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v4

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v4-tau

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

Suno chirp-v5

Suno text-to-music (chirp): generate a full song from a text prompt (and optional lyrics). Async; returns 2 variations.

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.

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/分钟

一个 API，畅享全模态 AI。

探索全部模型

Seed ASR 2.0 API by ByteDance

输入

输出

参数

代码示例

安装

认证

HTTP 请求头

提交请求

提交请求

请求体

响应

检查状态

轮询示例

状态值

完成响应

Input Schema

请求体示例

Output Schema

响应示例

Atlas Cloud Skills

支持的客户端

安装

设置 API Key

功能

MCP Server

支持的客户端

安装

配置

可用工具

API Schema

LLM 友好的提示词模板

Seed ASR 2.0 (Recording-File Recognition)

🌟 Key Features

🗣 High-Accuracy Transcription

🌍 51 Languages

🎯 Rich Output

📻 Far-Field Optimized

⚙️ Parameters

📤 Output

🎯 Use Cases

探索类似模型

Seed Audio 1.0

xAI TTS v1

ElevenLabs v3 Text-to-Speech

Suno chirp-auk

Suno chirp-fenix

Suno chirp-v3-0

Suno chirp-v3-5

Suno chirp-v3-5-tau

Suno chirp-v4

Suno chirp-v4-tau

Suno chirp-v5

MiniMax Music 2.6

xAI STT v1

一个 API，畅享全模态 AI。

Join our Discord community

输入

输出

参数

代码示例

安装

认证

HTTP 请求头

提交请求

提交请求

请求体

响应

检查状态

轮询示例

状态值

完成响应

Input Schema

请求体示例

Output Schema

响应示例

Atlas Cloud Skills

支持的客户端

安装

设置 API Key