MPG to SPH Converter

Extract NIST Sphere audio from MPG video online

Drop files here. 1 GB maximum file size or Sign Up
to
Facebook Amazon Microsoft Tesla Nestle Walmart L'Oreal

Research Standard

SPH (Sphere) is the cornerstone of speech research. Extract MPG audio in the format linguistic corpora and ASR tools expect.

Cloud-Based Work

Audio extraction runs on our servers — no NIST tools needed locally to produce Sphere-format files.

Data Privacy

Uploaded MPG files are removed after conversion. SPH outputs are deleted from servers within 24 hours.

How to convert MPG to SPH

1

Select files from Computer, Google Drive, Dropbox, URL or by dragging it on the page.

2

Choose sph or any other format you need as a result (more than 200 formats supported)

3

Let the file convert and you can download your sph file right afterwards

About formats

MPG is a common file extension for video files encoded using the MPEG-1 or MPEG-2 compression standards, developed by the Moving Picture Experts Group. The three-character extension originated from early Windows and DOS file systems that restricted extensions to three characters, providing a shorthand for the longer MPEG designation. MPG files contain MPEG program streams that multiplex one video and one or more audio elementary streams into a unified byte stream with synchronization timestamps. The format was widely used throughout the 1990s and 2000s for storing digital video on personal computers, appearing in everything from Video CD rips and DVD extractions to digital TV recordings captured with hardware encoder cards. MPG files using MPEG-1 compression typically contain 352x240 (NTSC) or 352x288 (PAL) video at bit rates around 1.5 Mbps, while MPEG-2 encoded MPG files support higher resolutions up to full HD. The program stream structure assumes a relatively reliable storage medium, unlike the transport stream variant designed for broadcast, making it efficient for file-based playback without the overhead of error recovery packets. Broad compatibility is one of the enduring strengths of the format, as virtually every media player across all operating systems can decode these files without additional codec installation. MPG continues to be encountered in archived video content, surveillance recordings, and legacy digital video workflows.
Initial release: August 1993
SPH is the file extension for audio stored in the NIST SPHERE (SPeech HEader REsources) format, a standard created by the U.S. National Institute of Standards and Technology around 1990. Built for speech research, SPH files carry a 1024-byte ASCII header packed with metadata — database identifiers, channel counts, sample rates, byte ordering, and compression type — making every recording self-describing. The underlying audio is typically 16-bit linear PCM sampled at 16 kHz, though other configurations are permitted. Researchers at NIST, DARPA, and universities worldwide rely on SPH for distributing speech corpora such as TIMIT, Switchboard, and the LDC collections that underpin modern automatic speech recognition systems. A key advantage is that the human-readable header lets scripts parse recording metadata without binary decoding. The format's strict standardization also eliminates ambiguity when sharing datasets across institutions and platforms. Because SPH files store uncompressed PCM, they preserve full audio fidelity — critical when training acoustic models where even small artifacts can skew results.
Initial release: 1990

Frequently Asked Questions

Why convert MPG to SPH?

SPH (NIST Sphere) is the standard format for speech research corpora. Converting produces audio compatible with linguistic research tools.

What uses SPH files?

The NIST speech tools, LDC corpora, Kaldi, and HTK speech recognition frameworks all work with Sphere-format audio.

Does SPH include metadata?

Yes — Sphere files have a rich text header that stores sample rate, encoding, channel count, and custom metadata fields.

Is SPH suitable for general playback?

SPH is a research format. Convert to WAV or MP3 for general listening. SPH is best for speech analysis pipelines.

Can I batch extract?

Upload multiple MPG files and extract SPH audio from each — build research datasets efficiently in one session.