On this page
Speech-to-text API for audio and video
Submit an audio or video file URL to create an asynchronous transcription. Use automatic speech recognition (ASR) for meeting recordings, interviews, podcasts, lectures and video subtitles. Include fileHeaders when the media source requires download headers.
Features
- No duration limit: no fixed limit in minutes for long recordings or videos, with a maximum file size of 1 GiB
- 99% accuracy: measured in testing; results vary with audio quality, language and content
- 99+ languages: automatic language detection or a language code of your choice
- Speaker recognition: automatically distinguish speakers in meetings and interviews
- Automatic timestamps: full text and timestamped segments for editing, search and subtitle generation
We use the ASR model ranked first in our evaluations and continually update our speech recognition capabilities.
Use your existing API key and API credits. Prices are listed in the Developer Console. For use from an AI agent, see MCP setup.
Endpoints and workflow
| Endpoint | Purpose |
|---|---|
POST /openapi/v1/transcriptions | Submit a media URL or uploaded audio ID and receive a task ID |
GET /openapi/v1/transcriptions/{id} | Query task status and results for free |
POST /openapi/v1/uploads | Get an upload ID and a PUT URL for local audio |
The API host is https://api.meowload.net. See the quickstart for authentication.
- Set
fileUrlto the audio or video file URL. IncludefileHeaderswhen the source requires headers such as Referer. - Call
POST /transcriptionsto get a task ID. Downloading, audio preparation and transcription run in the background. - Save the ID and GET every 3 seconds. Stop at
completedorfailed. A failed task still returns HTTP200; inspecterror. Stopping polling does not cancel the task.
For local audio, you can also use the file upload API, then create a transcription with the returned uploadId.
Inputs
Use Content-Type: application/json and choose either a media URL or an uploaded audio file as the source.
| Field | Rules |
|---|---|
fileUrl | Required for URL input; an HTTP(S) audio or video file URL |
fileHeaders | Optional headers for downloading the media file, such as Referer |
language | Optional, defaults to auto; supported codes such as en or zh, case-insensitive |
speakerLabels | Whether to distinguish speakers; optional boolean, defaults to false |
uploadId | Required for uploaded audio; obtained from the file upload API. Use instead of fileUrl and fileHeaders |
Original files and prepared audio are each limited to 1 GiB in both source modes.
The media URL must point directly to an audio file or a video with an audio track and remain valid during the background download. Use post extraction to get a media URL from a web page. Prefer a separate audio URL when available.
The full language code list is in the API reference.
Submit a media URL
This example uses a video source that requires Referer. Omit fileHeaders when the media URL can be downloaded directly.
curl https://api.meowload.net/openapi/v1/transcriptions \
-H 'Authorization: Bearer <your API key>' \
-H 'Content-Type: application/json' \
-d '{
"fileUrl": "https://media.example.com/meeting.mp4",
"fileHeaders": {"Referer": "https://example.com/"},
"language": "auto",
"speakerLabels": false
}'Submit local audio
Follow the file upload guide with mediaType set to audio, then use the returned uploadId:
curl https://api.meowload.net/openapi/v1/transcriptions \
-H 'Authorization: Bearer <your API key>' \
-H 'Content-Type: application/json' \
-d '{"uploadId":"0123456789abcdefghijklmn","language":"auto","speakerLabels":false}'Once the upload finishes, use uploadId to create a transcription task. You can reuse the same upload ID for other tasks while the file is available and belongs to your account.
Accepted response
{"id":"0123456789abcdefghijklmn","status":"processing"}Save the task ID and use it unchanged for subsequent queries.
Query and result
curl https://api.meowload.net/openapi/v1/transcriptions/0123456789abcdefghijklmn \
-H 'Authorization: Bearer <your API key>'Completed example with speaker labeling enabled:
{
"id": "0123456789abcdefghijklmn",
"status": "completed",
"duration": 15.2,
"language": "en",
"apiCreditsCost": 3,
"billingStatus": "settled",
"result": {
"text": "Hello everyone. Let's start our discussion.",
"segments": [
{"id": 0, "start": 0, "end": 3.2, "speaker": "speaker_0", "text": "Hello everyone. Let's start our discussion."}
]
},
"error": null
}| Field | Meaning |
|---|---|
status | processing, completed or failed |
duration | Audio duration in seconds; null before preparation completes |
language | Detected language at completion; null beforehand |
apiCreditsCost | Integer quote for this task; null until known. Preserved after a refund |
billingStatus | not_charged: no debit; reserved: debited; settled: successful; refunded: original debit returned |
result | Null before completion; otherwise original full text and segments. No source audio URL is returned |
result.segments | Times are seconds; start/end may be null when unavailable. Speaker labels are not guaranteed when disabled |
error | Null unless failed; then { "message": "…", "code": "snake_case" } |
Valid audio with no recognized speech may succeed with empty text and null or empty segments. You can use the segment text and timestamps to generate SRT/VTT subtitles.
Queries are free, including when your API credit balance is zero. Save the full text and segments for later use.
Billing and errors
Billing is based on audio duration, and API credits are reserved before execution. Preparation failures cost nothing. If the full balance is insufficient after preparation, the task fails with insufficient_api_credits; top up and submit again. It does not automatically resume after a top-up. An explicitly failed execution refunds the original reservation.
Asynchronous failure, HTTP 200:
{
"id": "0123456789abcdefghijklmn",
"status": "failed",
"duration": null,
"language": null,
"apiCreditsCost": null,
"billingStatus": "not_charged",
"result": null,
"error": {"message":"The video has no audio track","code":"audio_track_missing"}
}audio_track_missing means the video has no audio track; file_too_large means the size limit was exceeded. Download failures, preparation timeouts and transcription failures have their own reason codes. Branch on error.code, not the message text.
HTTP request failures use a non-200 response with {message, code?, detail?}: 401 for an invalid key, 402 for insufficient API credits, 422 for invalid parameters, 429 for per-key rate limits, and 503 when the service is unavailable before acceptance. See the API reference.
JavaScript: submit once and poll
Use Node.js fetch to submit a media URL and its headers, then query the task every 3 seconds.
const base = "https://api.meowload.net/openapi/v1"
const headers = { Authorization: "Bearer <your API key>" }
const response = await fetch(`${base}/transcriptions`, {
method: "POST",
headers: { ...headers, "Content-Type": "application/json" },
body: JSON.stringify({
fileUrl: "https://media.example.com/meeting.mp4",
fileHeaders: { Referer: "https://example.com/" },
language: "auto",
speakerLabels: false,
}),
})
if (!response.ok) throw new Error(`Create failed: ${response.status} ${await response.text()}`)
const { id } = await response.json()
console.log("Save this task ID:", id)
for (;;) {
await new Promise(resolve => setTimeout(resolve, 3000))
const query = await fetch(`${base}/transcriptions/${id}`, { headers })
if (!query.ok) throw new Error(`Query failed: ${query.status} ${await query.text()}`)
const task = await query.json()
if (task.status === "processing") continue
if (task.status === "failed") throw new Error(`${task.error.code}: ${task.error.message}`)
console.log(task.result.text)
break
}