Skip to Content
AnySolver logo
AnySolver
Recognition

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

  • body is the audio file as base64, without a data: prefix.
  • lang is the language spoken in the recording: en, fr, de, el, pt or ru.

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

ProviderPrice per 1,000Routing
2Captcha
$0.50

Request Schema

FieldTypeRequiredDescription
clientKey*
stringYes

Your API key. Create one in a workspace of the AnySolver dashboard.

Example: your-api-key-from-dashboard

task*
objectYes

The task body. Required fields depend on the task type. See Tasks for per-task schemas.

View task properties
settings
objectNo

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:

FieldTypeRequiredDescription
type*
Yes
body*
stringYes

Base64-encoded MP3 audio file, without a data URI prefix. Maximum size is 1 MB; duration is not limited.

Example: SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Ljc2LjEwMAAA...

lang*
Yes

Language spoken in the recording: en (English), fr (French), de (German), el (Greek), pt (Portuguese) or ru (Russian).

Example: en

{
    "clientKey": "YOUR_API_KEY",
    "task": {
        "type": "AudioRecognition",
        "body": "SUQzBAAAAAAAI1RTU0UAAAAPAAADTGF2ZjU4Ljc2LjEwMAAA...",
        "lang": "en"
    }
}

Optional fields are not guaranteed across providers

Required fields are guaranteed across every provider that supports this task. Optional fields may be honored by some providers and silently ignored by others. AnySolver does not document per-provider parameter support, so before relying on an optional field, check that provider's own docs for the task you are using.

Response Schema

FieldTypeRequiredDescription
status*
Yes

Task status: "processing", "ready", or "failed".

Example: ready

errorId*
Yes

0 on success; 1 or 2 on an error. Branch on errorCode: Error IDs explains the two error groups.

Example: 0

taskId
stringNo

Unique identifier returned when the task was created.

Example: 01KFNDF328KAN2AJ3BNHCQYE88

errorCode
No

Machine-readable error code.

Example: CAPTCHA_UNSOLVABLE

errorDescription
stringNo

Human-readable error message with resolution hints.

Example: The captcha could not be solved.

cost
numberNo

Actual cost charged for this task in USD.

Example: 0.002

taskType
No

The type of CAPTCHA task to solve.

Example: ReCaptchaV2TokenProxyLess

provider
No

Provider that handled this task. While processing, the provider currently solving it.

Example: Multibot

solution
objectNo

Solution Object Properties

The solution field contains an object with the following properties:

FieldTypeRequiredDescription
text*
stringYes

Text recognized from the audio recording.

Example: hello world

raw*
Record<string, unknown>Yes

Raw provider response data for advanced use cases.