Try Live STT Models

Test AWS Transcribe Live

Upload your own audio file (not huge for now) and get an instant transcript from AWS Transcribe. No login required.

Try AWS Transcribe on your audio

Drop a file below. We have pre-selected AWS Transcribe for you.

Input Source

Click or drag audio file here

Supports MP3, M4A, WAV, OGG

Max file size: 100MB

Configuration

Active Providers

AWS Transcribe

Input Language

Processing Options

Normalize AudioAuto-convert to 16kHz WAV mono for best results

Advanced Options

Use Native Configuration Mode

Enables raw parameter access for AWS Transcribe. Disables universal options.

Speaker Diarization

Identifies different speakers in the audio and labels their speech.

Speaker Count Hint

Min Speakers

Max Speakers

Provides a hint for the minimum and maximum number of expected speakers to improve diarization accuracy.

Custom VocabularyNot supported by all selected

Boosts the recognition probability of specific words or phrases, such as proper nouns or domain-specific terms. Provide one phrase per line.

Filter ProfanityNot supported by all selected

Detects and masks profane words in the transcript.

Smart FormattingNot supported by all selected

Converts transcribed numbers, dates, and currency into a more readable format (e.g., "twenty dollars" becomes "$20").

Automatic PunctuationNot supported by all selected

Automatically inserts punctuation like periods, commas, and question marks into the transcript.

Note: Files and transcripts are not stored on our servers and are used only to complete your request. More features are coming.

Technical Specifications

Configurable Parameters

These universal options are mapped to provider-specific features.

languagestring

Language

Primary language of the audio

Capabilities

Diarization
Diarization_config

Native Configuration

These are the provider's native API parameters — shown exactly as exposed by the vendor.

show_speaker_labelsDefault: false

Enable speaker diarization to identify and label different speakers in the transcription.

max_speaker_labelsDefault: 2

Maximum number of speakers to identify (2-10). Only used when Show Speaker Labels is enabled.

channel_identificationDefault: false

Identify which channel the speech belongs to in a multi-channel audio file.

show_alternativesDefault: false

Return alternative transcriptions for each segment.

max_alternativesDefault: 2

Maximum number of alternative transcriptions to return (2-10). Only used when Show Alternatives is enabled.

vocabulary_name

Name of a custom vocabulary you have created in AWS Transcribe to improve transcription accuracy for domain-specific terms.

vocabulary_filter_name

Name of a custom vocabulary filter you have created in AWS Transcribe to remove or mask specific words or phrases.

vocabulary_filter_methodDefault: remove

How to handle words that match the vocabulary filter. Only used when Vocabulary Filter is set.

About AWS Transcribe

AWS Transcribe automatic speech recognition service with support for multiple languages and speaker diarization

Pricing

A detailed pricing breakdown will be available here shortly. For now, please refer to the provider's official website.

View AWS Transcribe official documentation