TTS Phonetics Architect: Multilingual Lexicons & G2P

Omilia; Arizona; On-site; USD 90,000 - 130,000; Full time

Benefits offered by this job

Fixed compensation

Long-term employment with vacation

Professional development

Job summary

Omilia is seeking an expert in linguistics to ensure high-quality multilingual TTS output for American Spanish and other languages. You will design phoneme inventories, build pronunciation lexicons, and audit audio corpora to support enterprise-grade voice experiences.

You will collaborate with TTS engineers, data scientists, and native-speaker reviewers, documenting language-specific features and mapping phonemes to IPA. A strong background in phonetics and G2P is required.

Qualifications

• M.Sc. or Ph.D. in Linguistics, Phonetics, Computational Linguistics, or related field.
• Proven experience building pronunciation lexicons or G2P systems for TTS or ASR.
• Deep knowledge of phonological theory, articulatory and acoustic phonetics.
• Proficiency with IPA and machine-readable phoneme notation systems (X-SAMPA, ARPAbet, etc.).
• Experience with corpus annotation tools (Praat, ELAN, WebAnno, etc.).
• Fluency in English; proficiency in at least one additional language.
• Technical skills: Praat, ELAN, Audacity, PLS/CMUdict/SSML lexicon formats, Phonetisaurus/Sequitur/neural G2P, basic Python or shell scripting, TTS text normalization.

Responsibilities

• Conduct phonological and phonetic analysis of American Spanish.
• Document language-specific features (prosody, stress, tone, coarticulation, dialect variation).
• Produce language profiles for TTS model training and evaluation.
• Define and maintain phoneme inventories; map to IPA and TTS conventions.
• Audit corpora and select audio references for target voice tuning.
• Build and maintain pronunciation lexicons, including G2P rules.
• Review machine-generated G2P outputs; conduct pronunciation audits.
• Annotate audio corpora, develop evaluation protocols, and produce error analyses.
• Define linguistic criteria for TTS corpus selection and data collection prompts.
• Collaborate with TTS engineers to integrate linguistic artifacts into synthesis pipelines.
• Contribute to internal documentation and research discussions.

Skills

Phonological analysis

Phonetic analysis

G2P systems experience

Analytical skills

Documentation skills

Fluency in English

Multilingual capability

Education

M.Sc. or Ph.D. in Linguistics, Phonetics, Computational Linguistics, or related field

Tools

Praat

ELAN

Audacity

Python scripting

Shell scripting

Phonetisaurus/Sequitur

Job description

Omilia is seeking an expert in linguistics to ensure high-quality multilingual TTS output for American Spanish and other languages. You will design phoneme inventories, build pronunciation lexicons, and audit audio corpora to support enterprise-grade voice experiences.

You will collaborate with TTS engineers, data scientists, and native-speaker reviewers, documenting language-specific features and mapping phonemes to IPA. A strong background in phonetics and G2P is required.