Rupam Creator Studio for AI Assisted Content Production and Multilingual Captioning | IJCT Volume 13 – Issue 5 | IJCT-V13I5P53
IJCT
International Journal of Computer Techniques
ISSN 2394-2231 · Peer-Reviewed · Open Access
📚 Volume 13, Issue 5
📅 October 15, 2026
📄 Pages 463–469
🔖 ID: IJCT-V13I5P53
Rupam Creator Studio for AI Assisted Content Production and Multilingual Captioning
Author(s)
DR. T. CYNTHIA ANBUSELVI, KOTA SANTHOSH, A.N.TEJA, KEERTHI A.S, KRISHTIPATI PRAHARSHITHA, ANUPRIYA . M
Abstract
Short video production requires creators to move between topic research, writing, visual generation and caption editing. Rupam Creator Studio connects these activities through a web application with reusable creator context and editable intermediate outputs. The system combines public-source research, structured script generation, thumbnail and avatar service integrations, and a multilingual caption editor. Its caption pipeline separates speech recognition, acoustic alignment, text revision and rendering so that design changes do not require a new transcription request. A persistent local worker processes caption jobs, while Supabase supports authenticated asset storage and library records. This paper describes the implemented architecture, data flow and failure handling, and reports a local regression run in which 29 software checks passed. The result supports specific functional properties, including source-link validation, revision handling and job recovery; it does not establish transcription accuracy or creative effectiveness. The contribution is an integrated, human-reviewed production workflow rather than a new generative model.
Keywords
generative AI, creator tools, script generation, speech recognition, multilingual captions, media workflows.
Conclusion
Rupam Creator Studio integrates research-assisted script writing, thumbnail generation, ComfyUI-based avatar preparation and multilingual caption editing within one creator workspace. Shared context and editable intermediate outputs connect the stages, while revision snapshots, ownership checks and recoverable job handling support dependable processing. All 29 local regression checks passed, providing evidence for the exercised software contracts rather than for model accuracy or audience impact. The contribution is the coordinated application workflow built around existing AI services. Future work should evaluate transcription and timing against human references, assess avatar synchronization and creator usability, and extend job coordination across multiple hosts.
References
[1] A. Vaswani et al., “Attention Is All You Need,” arXiv:1706.03762,
2017. doi: 10.48550/arXiv.1706.03762.
[2] T. B. Brown et al., “Language Models are Few-Shot Learners,” arXiv:2005.14165, 2020. doi: 10.48550/arXiv.2005.14165.
[3] L. Ouyang et al., “Training language models to follow instructions with human feedback,” arXiv:2203.02155, 2022. doi: 10.48550/arXiv.2203.02155.
[4] J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” arXiv:2201.11903, 2022. doi: 10.48550/arXiv.2201.11903.
[5] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge Intensive NLP Tasks,” arXiv:2005.11401, 2020. doi: 10.48550/arXiv.2005.11401. 6 Generation In The Wild,” arXiv:2008.10010, 2020. doi:
[6] S. Yao et al., “ReAct: Synergizing Reasoning and Acting in Language Models,” International Conference on Learning Representations, 2023. https://arxiv.org/abs/2210.03629
[7] T. Schick et al., “Toolformer: Language Models Can Teach Themselves to Use Tools,” arXiv:2302.04761, 2023. doi: 10.48550/arXiv.2302.04761.
[8] A. Madaan et al., “Self-Refine: Iterative Refinement with Self Feedback,” arXiv:2303.17651, 2023. doi: 10.48550/arXiv.2303.17651.
[9] J. Maynez, S. Narayan, B. Bohnet, and R. McDonald, “On Faithfulness and Factuality in Abstractive Summarization,” arXiv:2005.00661, 2020. doi: 10.48550/arXiv.2005.00661.
[10] W. Kryściński, B. McCann, C. Xiong, and R. Socher, “Evaluating the Factual Consistency of Abstractive Text Summarization,” arXiv:1910.12840, 2019. doi: 10.48550/arXiv.1910.12840.
[11] A. Baevski, H. Zhou, A. Mohamed, and M. Auli, “wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations,” arXiv:2006.11477, 2020. doi: 10.48550/arXiv.2006.11477.
[12] A. Radford et al., “Robust Speech Recognition via Large-Scale Weak Supervision,” arXiv:2212.04356, 2022. doi: 10.48550/arXiv.2212.04356.
[13] U. Hermjakob, J. May, and K. Knight, “Out-of-the-box Universal Romanization Tool uroman,” Proceedings of ACL 2018, System Demonstrations, pp. 13–18, 2018. doi: 10.18653/v1/P18-4003.
[14] R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” arXiv:2112.10752, 2021. doi: 10.48550/arXiv.2112.10752.
[15] K. R. Prajwal, R. Mukhopadhyay, V. P. Namboodiri, and C. V. Jawahar, “A Lip Sync Expert Is All You Need for Speech to Lip 10.48550/arXiv.2008.10010.
[16] Supabase, “Storage Buckets,” documentation, accessed Sep. 26,
2026. https://supabase.com/docs/guides/storage/buckets/fundamentals
[17] Comfy, “The ComfyUI interface,” documentation, accessed Sep. 26, 2026. https://support.comfy.org/articles/7675456845-the-comfyui interface
[18] Sarvam AI, “Speech to Text REST API,” documentation, accessed Sep. 26, 2026. https://docs.sarvam.ai/api-reference/speech-to text/transcribe
[19] Descript, "Features," product documentation, accessed Oct. 10,
2026. https://www.descript.com/features
[20] Descript, "Video Caption Generator," product documentation, accessed Oct. 10, 2026. https://www.descript.com/tools/video caption-generator
[21] Descript, "Add Text to Video," product documentation, accessed Oct. 10, 2026. https://www.descript.com/tools/add-text-to-video
[22] VEED, "Video Editing Tools," product documentation, accessed Oct. 10, 2026. https://www.veed.io/tools
[23] VEED, "How to Create a New Project in VEED," Help Center, accessed Oct. 10, 2026. https://support.veed.io/en/articles/16413135 how-to-create-a-new-project-in-veed
[24] VEED, "How VEED’s dashboard works," Help Center, accessed Oct. 10, 2026. https://support.veed.io/en/articles/11641509-how veed-s-dashboard-works
2017. doi: 10.48550/arXiv.1706.03762.
[2] T. B. Brown et al., “Language Models are Few-Shot Learners,” arXiv:2005.14165, 2020. doi: 10.48550/arXiv.2005.14165.
[3] L. Ouyang et al., “Training language models to follow instructions with human feedback,” arXiv:2203.02155, 2022. doi: 10.48550/arXiv.2203.02155.
[4] J. Wei et al., “Chain-of-Thought Prompting Elicits Reasoning in Large Language Models,” arXiv:2201.11903, 2022. doi: 10.48550/arXiv.2201.11903.
[5] P. Lewis et al., “Retrieval-Augmented Generation for Knowledge Intensive NLP Tasks,” arXiv:2005.11401, 2020. doi: 10.48550/arXiv.2005.11401. 6 Generation In The Wild,” arXiv:2008.10010, 2020. doi:
[6] S. Yao et al., “ReAct: Synergizing Reasoning and Acting in Language Models,” International Conference on Learning Representations, 2023. https://arxiv.org/abs/2210.03629
[7] T. Schick et al., “Toolformer: Language Models Can Teach Themselves to Use Tools,” arXiv:2302.04761, 2023. doi: 10.48550/arXiv.2302.04761.
[8] A. Madaan et al., “Self-Refine: Iterative Refinement with Self Feedback,” arXiv:2303.17651, 2023. doi: 10.48550/arXiv.2303.17651.
[9] J. Maynez, S. Narayan, B. Bohnet, and R. McDonald, “On Faithfulness and Factuality in Abstractive Summarization,” arXiv:2005.00661, 2020. doi: 10.48550/arXiv.2005.00661.
[10] W. Kryściński, B. McCann, C. Xiong, and R. Socher, “Evaluating the Factual Consistency of Abstractive Text Summarization,” arXiv:1910.12840, 2019. doi: 10.48550/arXiv.1910.12840.
[11] A. Baevski, H. Zhou, A. Mohamed, and M. Auli, “wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations,” arXiv:2006.11477, 2020. doi: 10.48550/arXiv.2006.11477.
[12] A. Radford et al., “Robust Speech Recognition via Large-Scale Weak Supervision,” arXiv:2212.04356, 2022. doi: 10.48550/arXiv.2212.04356.
[13] U. Hermjakob, J. May, and K. Knight, “Out-of-the-box Universal Romanization Tool uroman,” Proceedings of ACL 2018, System Demonstrations, pp. 13–18, 2018. doi: 10.18653/v1/P18-4003.
[14] R. Rombach, A. Blattmann, D. Lorenz, P. Esser, and B. Ommer, “High-Resolution Image Synthesis with Latent Diffusion Models,” arXiv:2112.10752, 2021. doi: 10.48550/arXiv.2112.10752.
[15] K. R. Prajwal, R. Mukhopadhyay, V. P. Namboodiri, and C. V. Jawahar, “A Lip Sync Expert Is All You Need for Speech to Lip 10.48550/arXiv.2008.10010.
[16] Supabase, “Storage Buckets,” documentation, accessed Sep. 26,
2026. https://supabase.com/docs/guides/storage/buckets/fundamentals
[17] Comfy, “The ComfyUI interface,” documentation, accessed Sep. 26, 2026. https://support.comfy.org/articles/7675456845-the-comfyui interface
[18] Sarvam AI, “Speech to Text REST API,” documentation, accessed Sep. 26, 2026. https://docs.sarvam.ai/api-reference/speech-to text/transcribe
[19] Descript, "Features," product documentation, accessed Oct. 10,
2026. https://www.descript.com/features
[20] Descript, "Video Caption Generator," product documentation, accessed Oct. 10, 2026. https://www.descript.com/tools/video caption-generator
[21] Descript, "Add Text to Video," product documentation, accessed Oct. 10, 2026. https://www.descript.com/tools/add-text-to-video
[22] VEED, "Video Editing Tools," product documentation, accessed Oct. 10, 2026. https://www.veed.io/tools
[23] VEED, "How to Create a New Project in VEED," Help Center, accessed Oct. 10, 2026. https://support.veed.io/en/articles/16413135 how-to-create-a-new-project-in-veed
[24] VEED, "How VEED’s dashboard works," Help Center, accessed Oct. 10, 2026. https://support.veed.io/en/articles/11641509-how veed-s-dashboard-works
📋 How to Cite This Paper
DR. T. CYNTHIA ANBUSELVI, KOTA SANTHOSH, A.N.TEJA, KEERTHI A.S, KRISHTIPATI PRAHARSHITHA, ANUPRIYA . M (2026). Rupam Creator Studio for AI Assisted Content Production and Multilingual Captioning. International Journal of Computer Techniques, 13(5), 463–469. ISSN: 2394-2231. DOI: https://doi.org/10.5281/zenodo.23389739
