Ae · Deepgram · Post · Listen · Transcribe

Name: Ae · Deepgram · Post · Listen · Transcribe
Price: 1.00 USD

1.00积分/次

ae_deepgram_post_listen_transcribe

使用 Deepgram 的语音转文本 API，将 URL 中的音频或视频文件转录为文本。

转录音频视频

1.00积分/次

价格说明

1.00积分/次

API 调用

通过统一工具网关发起同步请求，鉴权和计费由 AgentEarth 处理。

cURL

curl --request POST \
  --url 'https://api.agentearth.ai/v1/tools/run' \
  --header 'Authorization: Bearer $AGENTEARTH_API_KEY' \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "tool": "ae_deepgram_post_listen_transcribe",
  "input": {
    "tag": "xxx",
    "url": "xxx",
    "extra": "xxx",
    "model": "base-general",
    "redact": "xxx",
    "search": "xxx",
    "topics": "false",
    "diarize": "false",
    "intents": "false",
    "keyterm": "xxx",
    "replace": "xxx",
    "version": "latest",
    "encoding": "xxx",
    "keywords": "xxx",
    "language": "en",
    "numerals": "false",
    "dictation": "false",
    "punctuate": "false",
    "sentiment": "false",
    "summarize": "xxx",
    "utt_split": "0.8",
    "paragraphs": "false",
    "utterances": "false",
    "mip_opt_out": "false",
    "custom_topic": "xxx",
    "filler_words": "false",
    "measurements": "false",
    "multichannel": "false",
    "smart_format": "false",
    "custom_intent": "xxx",
    "diarize_model": "xxx",
    "detect_entities": "false",
    "detect_language": "xxx",
    "profanity_filter": "false",
    "custom_topic_mode": "extended",
    "custom_intent_mode": "extended"
  }
}'

请求方式: POST
接口地址: /v1/tools/run
鉴权方式: Bearer Token
超时时间: 60 秒
当前版本: —

响应示例

{
  "error_no": 0,
  "error_msg": "",
  "result": [
    {
      "type": "text",
      "text": "xxx"
    }
  ],
  "platform_annotations": {
    "source": "AgentEarth",
    "platform_note": "xxx",
    "platform_suggestion": "xxx"
  }
}

工具参数

未传入的可选参数将使用平台默认值。

参数	类型	必填	说明	默认值
`tag`	unknown	否	Label your requests for the purpose of identification during usage reporting	—
`url`	string	是	暂无参数说明。	—
`extra`	unknown	否	Arbitrary key-value pairs that are attached to the API response for usage in downstream processing	—
`model`	string	否	AI model used to process submitted audio	base-general
`redact`	unknown	否	Redaction removes sensitive information from your transcripts	—
`search`	unknown	否	Search for terms or phrases in submitted audio	—
`topics`	boolean	否	Detect topics throughout a transcript or text	false
`diarize`	boolean	否	Deprecated: use `diarize_model` instead. Recognize speaker changes. Each word in the transcript will be assigned a speaker number starting at 0.	false
`intents`	boolean	否	Recognizes speaker intent throughout a transcript or text	false
`keyterm`	array	否	Key term prompting can boost or suppress specialized terminology and brands. Only compatible with Nova-3	—
`replace`	unknown	否	Search for terms or phrases in submitted audio and replaces them	—
`version`	string	否	Version of an AI model to use	latest
`encoding`	enum (linear16 \| flac \| mulaw \| amr-nb \| amr-wb \| opus \| speex \| g729)	否	Specify the expected encoding of your submitted audio	—
`keywords`	unknown	否	Keywords can boost or suppress specialized terminology and brands	—
`language`	string	否	The [BCP-47 language tag](https://tools.ietf.org/html/bcp47) that hints at the primary spoken language. Depending on the Model and API endpoint you choose only certain languages are available	en
`numerals`	boolean	否	Numerals converts numbers from written format to numerical format	false
`dictation`	boolean	否	Dictation mode for controlling formatting with dictated speech	false
`punctuate`	boolean	否	Add punctuation and capitalization to the transcript	false
`sentiment`	boolean	否	Recognizes the sentiment throughout a transcript or text	false
`summarize`	unknown	否	Summarize content. For Listen API, supports string version option. For Read API, accepts boolean only.	—
`utt_split`	number	否	Seconds to wait before detecting a pause between words in submitted audio	0.8
`paragraphs`	boolean	否	Splits audio into paragraphs to improve transcript readability	false
`utterances`	boolean	否	Segments speech into meaningful semantic units	false
`mip_opt_out`	boolean	否	Opts out requests from the Deepgram Model Improvement Program. Refer to our Docs for pricing impacts before setting this to true. https://dpgr.am/deepgram-mip	false
`custom_topic`	unknown	否	Custom topics you want the model to detect within your input audio or text if present Submit up to `100`.	—
`filler_words`	boolean	否	Filler Words can help transcribe interruptions in your audio, like "uh" and "um"	false
`measurements`	boolean	否	Spoken measurements will be converted to their corresponding abbreviations	false
`multichannel`	boolean	否	Transcribe each audio channel independently	false
`smart_format`	boolean	否	Apply formatting to transcript output. When set to true, additional formatting will be applied to transcripts to improve readability	false
`custom_intent`	unknown	否	Custom intents you want the model to detect within your input audio if present	—
`diarize_model`	enum (latest \| v1 \| v2)	否	Select and enable a specific diarization model version. Specifying this parameter enables diarization and selects the model — you do not need to also set the deprecated `diarize=true` parameter. For batch, supported values are `latest` (currently v2), `v1`, and `v2`. For streaming, supported values are `latest` (currently v1) and `v1`; `v2` returns a validation error on streaming requests.	—
`detect_entities`	boolean	否	Identifies and extracts key entities from content in submitted audio	false
`detect_language`	unknown	否	Identifies the dominant language spoken in submitted audio	—
`profanity_filter`	boolean	否	Profanity Filter looks for recognized profanity and converts it to the nearest recognized non-profane word or removes it from the transcript completely	false
`custom_topic_mode`	enum (extended \| strict)	否	Sets how the model will interpret strings submitted to the `custom_topic` param. When `strict`, the model will only return topics submitted using the `custom_topic` param. When `extended`, the model will return its own detected topics in addition to those submitted using the `custom_topic` param	extended
`custom_intent_mode`	enum (extended \| strict)	否	Sets how the model will interpret intents submitted to the `custom_intent` param. When `strict`, the model will only return intents submitted using the `custom_intent` param. When `extended`, the model will return its own detected intents in the `custom_intent` param.	extended