Job DescriptionDepartment: AI/LLM Operations
NExperience: 1+ Years Captive / GCC International Voice
NLocation: WFO // 6 Days Working
NEmployment: 3-Month Contract
NRole Overview:
NEvaluate AI-powered Speech-to-Speech (S2S), Text-to-Speech (TTS), and real-time conversational voice agents. The role requires solid auditory skills to assess prosody, cadence, pronunciation, emotion, and other speech characteristics across global English dialects.
NKey Responsibilities:
N
n
Evaluate S2S and TTS outputs for intelligibility, rhythm, and conversational cadence. N
Assess tone, empathy, hesitation, inflection, irony, and emotional expression. N
Conduct pairwise audio preference evaluations. N
Verify lip-sync, multimodal synchronization, and acoustic scene consistency. N
Evaluate North American, British, Australian,



and international English accents. N
Document audio anomalies, unnatural vocal artifacts, distortion, and phonetic errors. N

nMandatory Requirements:
N
n
1+ years of dedicated international voice experience exclusively within a Captive/In-House GCC serving US/global clients. N
Robust auditory abilityto identify subtle vocal inflections, pitch, cadence, and articulation issues. N

nPreferred:
N
n
Background in phonetics, phonology, auditory acoustics, or speech-language pathology. N
Experience in voice quality analytics, acoustic data annotation, or speech synthesis evaluation. N
Additional multilingualcapability. N

📌 Hiring: Speech Faridabad (India)
🏢 Innodata
📍 India