STT: Speech recognition and transcription with Whisper
Transcribing audio files to text is now easier and cost-effective. You can use our free tool to convert audio to text quickly. This tool supports over 100 languages and works with many audio file formats like MP3 and WAV.
Fast and Efficient Transcriptions
Our speech-to-text tool is not only free but also fast.
Transcribe Audio Endpoint
POST /transcribe
Transcribe an audio file to text using the Whisper model. This endpoint can process a variety of audio formats, ensuring maximum flexibility for your transcription needs.
Request
- Endpoint:
/transcribe
- Method:
POST
- Content-Type:
multipart/form-data
Parameters
- audio (required): The audio file to be transcribed. Supported formats include:
- WAV
- MP3
- FLAC
- OGG
- M4A
- WebM
- AAC
- WMA
- AIFF
- CAF
Response
Upon successful transcription, the response will contain a JSON object with the transcribed text:
{
"transcription": "[The transcribed text from the audio file]"
}
Example Request
POST /transcribe
Content-Type: multipart/form-data
audio: <file: audio.mp3>
Example Response
{
"transcription": "This is the transcribed text from the audio file."
}