SPX to SPH Converter

Convert Speex audio to NIST SPH speech header format

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

Speech Corpus Format

Convert SPX recordings to the NIST SPHERE format — the gold standard for distributing speech research datasets worldwide.

Research Compatible

SPH files work with Kaldi, HTK, Praat, and all major speech processing toolkits used in NLP and acoustic research.

Data Privacy

Uploaded SPX files are erased after conversion. SPH outputs are deleted from servers within 24 hours.

How to convert SPX 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

Speex is an open-source audio codec purpose-built for speech compression, developed by Jean-Marc Valin under the Xiph.Org Foundation. First released in October 2002, it targets voice-over-IP, conferencing, and any scenario where spoken word needs to travel efficiently over a network. SPX files wrap Speex-encoded audio inside an Ogg container, pairing the codec's speech optimization with Ogg's streaming capabilities. Three sampling rates are supported — narrowband at 8 kHz, wideband at 16 kHz, and ultra-wideband at 32 kHz — along with variable bitrate encoding that adapts in real time to speech complexity. A standout advantage is its patent-free, BSD-licensed nature, which allowed developers to embed it freely in both commercial and open-source products. Speex also bundles acoustic echo cancellation, noise suppression, and automatic gain control, features that rival codecs typically delegate to external libraries. Although its creators officially recommend Opus) as a successor since 2012, Speex remains deployed in legacy VoIP systems, archived recordings, and embedded devices where its lightweight decoder footprint is still valued.
Initial release: October 15, 2002
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 SPX to SPH?

SPH (NIST SPHERE) is the standard format for speech research corpora. Converting from SPX prepares recordings for linguistic and acoustic research.

What is NIST SPHERE?

SPHERE (SPeech HEader Resources) was developed by NIST for standardized speech data distribution in research communities.

What tools work with SPH?

The NIST SPHERE toolkit, HTK, Kaldi, Praat, and major speech processing frameworks handle SPH files natively.

Is SPH used in speech recognition?

Yes — most major speech corpora (TIMIT, Switchboard, etc.) are distributed in SPH format for training recognition models.

Is the conversion free?

Yes — free on convertio.tools for standard usage.