Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

I'm Steve Rossi, a voice and audio specialist with 30+ years of professional performance, music production, and audio engineering. I record, evaluate, and annotate speech datasets used to train AI voice models, delivering studio-quality narration and speech while assessing outputs for naturalness, prosody, and emotional delivery. As both voice talent and engineer, I translate nuanced listening judgments into actionable feedback that improves text-to-speech systems, voice cloning models, and speech AI datasets. I collaborate across projects to ensure voice realism, consistent timing, and artifact-free audio, from broadcast-quality studio work to scalable AI data pipelines.…I'm Steve Rossi, a voice and audio specialist with 30+ years of professional performance, music production, and audio engineering. I record, evaluate, and annotate speech datasets used to train AI voice models, delivering studio-quality narration and speech while assessing outputs for naturalness, prosody, and emotional delivery. As both voice talent and engineer, I translate nuanced listening judgments into actionable feedback that improves text-to-speech systems, voice cloning models, and speech AI datasets. I collaborate across projects to ensure voice realism, consistent timing, and artifact-free audio, from broadcast-quality studio work to scalable AI data pipelines.

Steve Rossi

Voiceover Artist, Audio Engineer, Music Producer, +3





I'm Steve Rossi, a voice and audio specialist with 30+ years of professional performance, music production, and audio engineering. I record, evaluate, and annotate speech datasets used to train AI voice models, delivering studio-quality narration and speech while assessing outputs for naturalness, prosody, and emotional delivery. As both voice talent and engineer, I translate nuanced listening judgments into actionable feedback that improves text-to-speech systems, voice cloning models, and speech AI datasets. I collaborate across projects to ensure voice realism, consistent timing, and artifact-free audio, from broadcast-quality studio work to scalable AI data pipelines.…I'm Steve Rossi, a voice and audio specialist with 30+ years of professional performance, music production, and audio engineering. I record, evaluate, and annotate speech datasets used to train AI voice models, delivering studio-quality narration and speech while assessing outputs for naturalness, prosody, and emotional delivery. As both voice talent and engineer, I translate nuanced listening judgments into actionable feedback that improves text-to-speech systems, voice cloning models, and speech AI datasets. I collaborate across projects to ensure voice realism, consistent timing, and artifact-free audio, from broadcast-quality studio work to scalable AI data pipelines.

Available to hire

I’m Steve Rossi, a voice and audio specialist with 30+ years of professional performance, music production, and audio engineering. I record, evaluate, and annotate speech datasets used to train AI voice models, delivering studio-quality narration and speech while assessing outputs for naturalness, prosody, and emotional delivery.

As both voice talent and engineer, I translate nuanced listening judgments into actionable feedback that improves text-to-speech systems, voice cloning models, and speech AI datasets. I collaborate across projects to ensure voice realism, consistent timing, and artifact-free audio, from broadcast-quality studio work to scalable AI data pipelines.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

DaVinci Resolve Studio

Expert

Expert

Expert

Expert

Expert

Intermediate

Intermediate

Intermediate

Language

English

Fluent

Work Experience

Music Director & Program Leader at School of Rock

January 1, 2012 - Present

Managed and coordinated a team of up to 45 instructors and program directors; directed hundreds of live performances and large ensemble productions; evaluated musical performance focusing on timing, tone, phrasing, and stylistic accuracy; provided structured feedback improving performance execution and cohesion; designed rehearsal workflows used across multiple locations; mentored musicians and trained instructors on performance standards and rehearsal methods.

AI Voice & Speech Evaluation Specialist / Independent Contractor at Independent Contractor

January 1, 2023 - Present

Contributed to creation, evaluation, and refinement of speech datasets used to train and benchmark modern voice AI systems; evaluated speech, narration, and music datasets; annotated pitch accuracy, rhythm alignment, timbre classification, articulation, and speaker characteristics; assessed AI-generated voice outputs for naturalness, emotional alignment, pacing, and prosody; applied structured evaluation rubrics, developed prompts and evaluation rubrics; performed audio quality analysis including artifact detection, spectral consistency, and noise issues; scored and ranked model outputs to support benchmarking and dataset quality improvements.

AI Voice & Speech Evaluation Specialist at Independent Contractor

January 1, 2023 - Present

Self-employed contractor contributing to the creation, evaluation, and refinement of speech datasets for AI voice systems. I evaluate speech narration and music datasets, annotate pitch, rhythm, timbre, articulation, and speaker characteristics, assess AI-generated outputs for naturalness, emotional alignment, pacing, and realism, apply structured rubrics, develop evaluation prompts, and support dataset quality improvements with edge-case feedback.