Dumpling AI Extract Audio
90 credits/call
ae_dumplingai_extract_audio
Transcribe audio files or URLs and extract insights based on your instructions using DumplingAI.
90 credits/call
Pricing
90 credits/call
| Condition | Charge |
|---|---|
| Each call | 90 credits/call |
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
audio | string | Yes | Audio URL or base64-encoded audio content to analyze. | — |
prompt | string | Yes | Instructions describing the insights to extract from the audio. | — |
jsonMode | boolean | No | When true, requests the model to respond with JSON-formatted output. | false |
inputMethod | enum (url | base64) | Yes | Indicates whether binary content is supplied via URL or base64-encoded string. | — |
requestSource | enum (API | WEB | MAKE_DOT_COM | ZAPIER | N8N | PLAYGROUND | DEFAULT_AUTOMATION | AGENT_PREVIEW | AGENT_LIVE | AUTOPILOT | STUDIO) | No | Optional identifier describing where the API request originated. | — |
Invocation example
Copy the request and explore its response example.
POST
/agent-api/v1/tool/executeX-Api-KeyRequest coderequest.sh
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_dumplingai_extract_audio' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"audio": "https://api.mindtestlab.cloud/gequ-audio/av018.mp3",
"inputMethod": "url",
"prompt": "Listen to this music. 1) Describe it with concise English keywords: genre, mood, main instruments, tempo/BPM feel, energy level. 2) Transcribe any singing or spoken words exactly as heard (with language). If there is no singing, say '\''no vocals'\''."
}
}'Response exampleresponse.json
{
"audioDuration": 30.040816326530614,
"creditUsage": 120,
"prompt": "Listen to this music. 1) Describe it with concise English keywords: genre, mood, main instruments, tempo/BPM feel, energy level. 2) Transcribe any singing or spoken words exactly as heard (with language). If there is no singing, say 'no vocals'.",
"results": "Sure! Here's a description and transcription of the music:\n\n### **1) Keywords**\n* **Genre:** J-Pop, Pop Rock, Anime-style\n* **Mood:** Happy, Optimistic, Youthful, Energetic\n* **Main Instruments:** Acoustic guitar, Electric bass, Drums, Female vocals\n"
}This example shows part of the response. Copied content is valid JSON.

