AudioRecognition
Transcribe an audio CAPTCHA or any short MP3 recording to text. Send the base64 audio and its language, and read the recognised words back.
AudioRecognition transcribes a spoken recording and returns the text. Use it for audio CAPTCHAs, or for any short recording you need transcribed.
What to send
bodyis the audio file as base64, without adata:prefix.langis the language spoken in the recording:en,fr,de,el,ptorru.
Send MP3 audio of 1 MB or less. Convert other audio formats to MP3 before you encode them. A speech model transcribes the recording, not a human worker.
Read the answer
text holds the recognised text, for example hello world. Normalise it for the CAPTCHA you are solving, for instance by trimming spaces and applying the case the site expects.
Check Provider stats for live success rates and solve times before you pick a provider.
Supported Providers
| Provider | Price per 1,000 | Routing |
|---|---|---|
2Captcha | $0.50 |
Request Schema
| Field | Type | Required | Description |
|---|---|---|---|
clientKey* | string | Yes | Your API key. Create one in a workspace of the AnySolver dashboard. Example: |
task* | object | Yes | The task body. Required fields depend on the task type. See Tasks for per-task schemas. View task properties |
settings | object | No | Per-request settings for routing, Auto Retry, Auto Fallback, proxy reuse, response statistics and detailed analytics. Each field overrides the API key's value. See Routing modes. View settings reference |
Task Object Properties
The task field accepts an object with the following properties:
| Field | Type | Required | Description |
|---|---|---|---|
type* | Yes | ||
body* | string | Yes | Base64-encoded MP3 audio file, without a data URI prefix. Maximum size is 1 MB; duration is not limited. Example: |
lang* | Yes | Language spoken in the recording: en (English), fr (French), de (German), el (Greek), pt (Portuguese) or ru (Russian). Example: |
{
"clientKey": "YOUR_API_KEY",
"task": {
"type": "AudioRecognition",
"body": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Ljc2LjEwMAAA...",
"lang": "en"
}
}Optional fields are not guaranteed across providers
Response Schema
| Field | Type | Required | Description |
|---|---|---|---|
status* | Yes | Task status: "processing", "ready", or "failed". Example: | |
errorId* | Yes |
Example: | |
taskId | string | No | Unique identifier returned when the task was created. Example: |
errorCode | No | Machine-readable error code. Example: | |
errorDescription | string | No | Human-readable error message with resolution hints. Example: |
cost | number | No | Actual cost charged for this task in USD. Example: |
taskType | No | The type of CAPTCHA task to solve. Example: | |
provider | No | Provider that handled this task. While processing, the provider currently solving it. Example: | |
solution | object | No |
Solution Object Properties
The solution field contains an object with the following properties:
| Field | Type | Required | Description |
|---|---|---|---|
text* | string | Yes | Text recognized from the audio recording. Example: |
raw* | Record<string, unknown> | Yes | Raw provider response data for advanced use cases. |