AI Trainer Voice and Speech Evaluation
Inworld AI is a research lab and inference provider for realtime AI at consumer scale. It provides text-to-speech, speech-to-text, speech-to-speech, and LLM routing products for developers and businesses building consumer-facing applications.
Funding history
Projects
About Inworld AI
Inworld AI develops and operates realtime AI infrastructure, including first-party text-to-speech and speech-to-text models, a customizable speech-to-speech Realtime API, and an LLM Router that routes requests across leading model providers. Its platform supports voice agents, social and companion applications, learning and education, health and wellness, agentic workforce applications, and games and media. The company serves developers, businesses, and teams building consumer-facing applications.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will evaluate paired and grouped speech samples for naturalness, expressiveness, instruction fidelity, and audio quality. You will score voices against defined rubrics, label voice attributes, assess cloned-voice similarity, review voices before release, test pre-release speech features, report issues, and document clear findings for engineers.
Requirements
- Background in audio production, broadcast, voice acting, music, linguistics, phonetics, or a similar field
- Ability to identify and describe subtle differences in prosody, timing, pronunciation, and audio quality
- Ability to make consistent, careful judgments across large batches of samples
- Comfort with beta web tools, VPN access, and spreadsheets
- Strong written English
- Ability to complete tasks within a day when needed, including occasional weekend availability
Responsibilities
- Evaluate paired or grouped speech samples for naturalness, expressiveness, and instruction fidelity
- Score voices for naturalness, clarity, emotion, pacing, and delivery style
- Label voice attributes and flag metadata mismatches
- Assess how closely cloned voices match source speakers
- Review new voices for audio quality and release suitability
- Test pre-release speech features and report bugs, edge cases, and usability issues
- Write structured findings for engineers
- Evaluate pronunciation, dialect accuracy, and naturalness in a native language for multilingual roles