OpenAI Whisper
ae_whisper — Transcribe audio in its original language or translate speech into English with WaveSpeed Whisper. Provide an HTTPS audio URL or upload an MP3, WAV, or FLAC file up to 60 minutes long. Choose a supported language or use automatic detection, optionally add word-level timestamps, and provide a same-language prompt to guide transcription style or continue a previous segment. Timestamps may increase processing time. Speaker identification and diarization are not supported.
Pricing
The charge per call is (max(((1.2 * if (Enable word-level timestamps == true) then 0, otherwise min(ceil(Input audio duration (seconds)), 600)) + (2.4 * if (Enable word-level timestamps == true) then min(ceil(Input audio duration (seconds)), 600), otherwise 0)), 0)) AE credits. All applicable conditions are combined to calculate the total.
Charges are based on the actual input audio duration. Word-level timestamps are disabled by default; enabling them may increase processing time. Transcription in the original language or translation into English, language selection, and prompt text carry no separate charge.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
request_body | object | Yes | No parameter description. | — |
request_body.task | enum (transcribe | translate) | No | The task to perform. 'transcribe' to the source language or 'translate' to English. | transcribe |
request_body.audio | string | Yes | Audio file to transcribe. Provide an HTTPS URL or upload a file (MP3, WAV, FLAC up to 60 minutes). | — |
request_body.prompt | string | No | An optional text to provide as a prompt to guide the model's style or continue a previous audio segment. The prompt should be in the same language as the audio. | — |
request_body.language | enum (auto | af | am | ar | as | az | ba | be | bg | bn | bo | br | bs | ca | cs | cy | da | de | el | en | es | et | eu | fa | fi | fo | fr | gl | gu | ha | haw | he | hi | hr | ht | hu | hy | id | is | it | ja | jw | ka | kk | km | kn | ko | la | lb | ln | lo | lt | lv | mg | mi | mk | ml | mn | mr | ms | mt | my | ne | nl | nn | no | oc | pa | pl | ps | pt | ro | ru | sa | sd | si | sk | sl | sn | so | sq | sr | su | sv | sw | ta | te | tg | th | tk | tl | tr | tt | uk | ur | uz | vi | yi | yo | zh | yue) | No | Language spoken in the audio. Set to 'auto' for automatic language detection (default). | auto |
request_body.enable_timestamps | boolean | No | Enable to generate word-level timestamps for the transcription. Note: This may increase processing time. | false |
Invocation example
Copy the request and explore its response example.
/agent-api/v1/tool/executeX-Api-KeySubmit first, then query with the returned task_id until the task completes.
curl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_whisper' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"request_body": {
"audio": "https://agentearth.ai/fileserver/file/69c1edfd-4392-498d-9af5-b6c223b7fb99.wav",
"enable_timestamps": false,
"language": "zh",
"prompt": "不嫁给福清男人,怎么能吃到姜母鸭,哪来的幸福",
"task": "transcribe"
}
}
}'{
"description": "task accepted; poll the result via query_tool with this task_id",
"query_tool": "ae_get_result",
"status": "created",
"task_id": "94931a84-8d3b-4fb9-ab92-c3085e09a7c4"
}This example shows part of the response. Copied content is valid JSON.
Guides using this tool
See how this tool fits into real workflows







