We are looking for Speech & Audio AI Evaluation Specialists with 2+ years of dedicated International Voice experience within a Captive or Global Capability Centre (GCC) environment.

The role involves evaluating AI-generated speech and audio outputs, including Speech-to-Speech (S2S), Text-to-Speech (TTS), and conversational voice agents. Candidates should possess exceptional listening skills, solid command of international English, and the ability to identify nuances in pronunciation, tone, cadence, emotional expression, and accent.

Key Responsibilities

- Evaluate Speech-to-Speech (S2S) and Text-to-Speech (TTS) outputs for naturalness, intelligibility, rhythm, and conversational flow.
- Assess tone, emotional expression, empathy, hesitation, inflection, irony, and other paralinguistic elements.
- Conduct side-by-side comparisons and preference ratings of different audio outputs.
- Identify and document audio anomalies, pronunciation issues, unnatural vocal artifacts, distortion, and phonetic inaccuracies.




- Evaluate and calibrate different English accents and dialects, including North American, British, Australian, and other international English variations.
- Support multimodal validation activities, including audio-video synchronization and lip-sync evaluation.
- Provide clear and detailed evaluation rationales based on defined quality guidelines.

Candidate Requirements

- 2+ years of dedicated International Voice Process experience.
- Experience must be from a Captive / In-House GCC environment serving US or global customers.
- Strong auditory skills with the ability to identify subtle differences in pitch, cadence, articulation, and vocal expression.
- Experience in Voice QA, Speech Quality Analysis, Audio Annotation, Speech Evaluation, Linguistics, Phonetics, or Speech Synthesis will be an added advantage.
- Additional multilingual capabilities will be preferred.

📌 Speech & Audio AI Evaluation Specialist - International Voice (Noida)
🏢 Innodata India
📍 Noida