Best Practices

This section is designed to provide guidelines for achieving the best speech-to-text results possible when using the API.

File formats

Rev AI uses FFmpeg and therefore supports all the file formats supported by FFmpeg. This includes all common media formats, such as MP3, MP4, Ogg, WAV, PCM and FLAC and many more. For best results, use a lossless format such as FLAC or ALAC, or a lossy format like MP3 or AAC with a bitrate of 192 Kbps or above.

Sampling rate

If you control the audio source, record at 16kHz sample rate or higher. We can transcribe audio as low as 8kHz as well. Do not up-sample or down-sample audio. Submit the audio in its original format.

Multi-channel audio

For perfect speaker separation (speaker diarization), record each speaker on their own channel and submit the job using the speaker_channels_count parameter. If the speakers are recorded on a single channel, do not attempt to modify the recording; submit the file as is.

warning

Speaker channels incur extra costs as outlined in the Asynchronous Speech-to-Text API documentation.

Preprocessing audio

Don't pre-process audio. This can distort the audio and reduce the transcript accuracy. Our speech engine is very robust and has been designed to handle a large variety of audio recordings.

Uncommon words

To improve recognition of uncommon words, such as proper names and special technical terms, submit a list of these words as custom vocabulary along with your request. Read the Custom Vocabulary API documentation for more details.