Pixazo API→MP4 to MP3 API

MP4 to MP3 API

Convert MP4 to MP3 — and pull the audio track out of any video — with a single API call. The MP4 to MP3 API returns a clean, standalone MP3 (or WAV, AAC or FLAC) from your video, built for podcast repurposing, transcription pipelines, meeting and webinar archives, and anywhere you need just the sound from a clip. No desktop converter, no manual export, no re-uploading gigabytes of video.

Explore Models

Explore MP4 to MP3 API Models

We’re onboarding models for MP4-to-MP3 conversion and audio extraction. Until they’re live, here’s exactly what the MP4 to MP3 API is being built to do.

Browse by Capabilities

Coming soon

MP4 to MP3 API models are on the way

Convert MP4 to MP3 and extract the audio track from any video via API. We're adding models to this category — check back soon.

Browse available models →
In active development · Coming soon

Convert MP4 to MP3 — extract clean audio from any video

The MP4 to MP3 API will take a video file and return only its audio — an MP3 by default — in one call. Instead of downloading a video, opening a desktop converter, exporting the audio and re-uploading it, you make a single request and get back exactly the track you need.

MP4 to MP3 is the most common job, but it is not limited to it: the API also converts MOV, MKV and WebM to MP3 (or WAV, AAC and FLAC), so any video-to-MP3 workflow runs through the same endpoint. It is built for podcasters turning video interviews into episodes, teams archiving meeting and webinar audio, and anyone preparing audio for transcription — and because the source video is never modified, it slots safely into an existing pipeline.

What will the MP4 to MP3 API return?

Planned outputTypical settingsBest for
MP3 (compressed)128–320 kbps, stereoPodcasts, web playback, sharing
AAC (compressed)128–256 kbpsMobile & streaming delivery
WAV / FLAC (lossless)44.1 / 48 kHzEditing, mastering, archival
Mono downmix + timestamps16 kHz monoSpeech-to-Text pre-processing

How will it work?

  1. Send a video URL (or upload) to the endpoint with your API key in the Authorization header.
  2. Choose the target format, sample rate, bitrate and channel layout.
  3. The job runs asynchronously — poll its status or receive a webhook.
  4. Download the extracted audio; your source video stays untouched.

What people will use it for

›Convert MP4 recordings to MP3 for podcasts and audio feeds
›Prepare audio for the Speech to Text API and captioning
›Archive meeting and webinar audio separately from the video
›Batch-convert a video library to MP3 for search and datasets
What it won’t do: This endpoint converts and separates existing audio — it does not transcribe speech (use the Speech to Text API), remove background noise, or isolate individual instruments or speakers. Those are separate capabilities.

Questions people ask

When will the MP4 to MP3 API be available?
It is in active development. This page is published so you can plan your integration now; the endpoint, parameters and pricing will appear here the moment it ships. No working conversion is offered today.
What formats besides MP3 will it output?
MP3 is the default, with WAV, AAC and FLAC also planned, plus control over sample rate (e.g. 44.1 kHz, 48 kHz), bitrate, and channels (stereo or mono downmix). The confirmed list will be published at launch.
Does it only accept MP4, or other video formats too?
MP4 is the headline input, but MOV, MKV and WebM are planned as well — the API extracts the audio track regardless of the video container, so “MP4 to MP3” is the common case, not the only one.
Will it keep the original video?
Yes — conversion is non-destructive. You send a video URL or upload and receive only the audio (e.g. the MP3); your source video is never altered or re-encoded.
Can I send a remote URL instead of uploading?
Yes. Both a direct upload and a public/pre-signed URL are planned as inputs, so you can convert files already in your storage without moving them.
Will the MP3 feed the Speech to Text API?
That is a core use case. A mono, timestamp-friendly downmix is planned specifically so the converted audio can be passed straight into transcription.