How one of Brazil’s largest TV networks automated the transcription of its content with GenAI
- Marcelo Firpo
- Feb 26
- 4 min read
Advanced automation in news transcription Reduced operational costs and increased efficiency Accuracy and impartiality in the generation of summaries
AI generated summary:
One of Brazil’s largest television networks faced challenges in transcribing and summarizing news reports, impacting operational efficiency and multiplatform content distribution. In partnership with BlueMetrics, the broadcaster implemented a Generative AI-based solution using AWS Transcribe and Bedrock to automate the conversion of audio to text and generate unbiased summaries.
Overview
The client is one of the largest television networks in Brazil, with a significant national presence through more than a hundred stations, both owned and affiliated. With a strong presence in investigative journalism and police-related programs, the network stands out for its intensive coverage of criminal cases and investigative stories.
In a market of accelerated consumption of digital news, the client was looking for a solution that would increase its operational efficiency, guarantee the impartiality of the content and optimize the multiplatform distribution of the reports.
Market context:
Need to transform audiovisual content into text
Growing demand for accessible and structured digital content
Agility in providing journalistic information
Evolution of digital journalism and the need for editorial standardization
Problem: How to make news processing more efficient?
The manual process of transcribing and summarizing audiovisual content required considerable resources and extensive time, impacting the agility in the multiplatform distribution of content and its subsequent use in other journalistic productions.
According to Gabriel Casara, CGO at BlueMetrics, "This is a very common pain point in organizations that need to deal with large volumes of unstructured data, in this case, content. But it also applies to a wide variety of companies, in segments as diverse as Education, Health and Finance."
Main challenges:
Operational limitations:
Manual transcription process requiring exclusive dedication from professionals
Long time between content production and its availability in text format
Inconsistency in standardization of abstracts due to different writing styles
Difficulty in maintaining a standard of impartiality in transcripts and summaries
Business limitations:
Underutilization of journalistic collections due to lack of structured documentation
High operational costs with dedicated transcription staff
Delays in making content available on other platforms
Difficulty in scaling content production for different channels
Technological limitations:
Lack of an automated solution for large-scale audio processing
Lack of tools that guarantee neutrality and impartiality in content summarization
Complexity in integrating different media formats and systems
Need for specialized processing for specific language of police journalism
The Solution: Generative AI for Automated Transcription and Summarization
BlueMetrics has developed an automated audiovisual content transcription and summarization solution, using AWS cloud services to process criminal reports and generate neutral and impartial summaries, maintaining journalistic integrity.
According to Diórgenes Eugênio, Head of Gen AI at BlueMetrics, “In addition to the complexity of transcribing audiovisual content with high accuracy, we had to ensure that the summaries generated did not express any bias or opinion. This was the biggest challenge, as even small details could compromise the required neutrality. We used AWS Transcribe to convert the audio to text. After transcription, we moved on to the second component: generating unbiased summaries. Here, the challenge was to ensure that the model did not infer subjective interpretations or draw conclusions about the facts. We used AWS Bedrock to integrate fact-based summarization techniques. The combination of Transcribe, Bedrock, and our custom validation layer was essential to deliver a pipeline aligned with the broadcaster’s requirements.”
Main Components:
Automated audio-to-text processing system
Abstract generation engine with neutrality control
Scalable asynchronous processing pipeline
Structured database for storage and consultation
Automated data input and output flow
Technological Differentials:
Using specialized AI to transcribe audio into Portuguese
Use of generative AI in the summarization of extracted texts
Serverless architecture with on-demand processing
Native integration with existing infrastructure
Immediate Benefits:
Significant reduction in content processing time
Standardization in the quality of generated summaries
Guarantee of neutrality and impartiality
Automatic scalability on demand
Optimization of operational resources
Faster availability of content in text format
How about developing a solution like this for your company?
Results:
The implementation of the automated solution had a direct impact on the productivity of the client’s editorial team, significantly reducing the time required to transcribe and summarize criminal reports.
As a result, the broadcaster began to make its content available in multiple formats more quickly and efficiently, meeting the growing demand of the digital market. In addition, the adoption of AI ensured a higher level of standardization and impartiality, factors essential for the credibility of investigative journalism.
By optimizing the workflow, the solution allowed journalists to focus on strategic activities instead of repetitive tasks, increasing the capacity to produce new content. The structuring and organization of the extracted data also facilitated the reuse of journalistic material, increasing the value of the broadcaster's archive.
Operational Efficiency:
Complete automation of the transcription process
Significant reduction in content processing time
Freeing up teams for strategic activities
Standardization in reporting documentation
Editorial Quality:
Guarantee of neutrality and impartiality in summaries
Consistency in the language and format of the generated texts
Greater accuracy in documenting criminal cases
Maintenance of the broadcaster's journalistic standards
Content Management:
Structured documentation of the journalistic collection
Ease of retrieving historical information
Better organization of the material produced
Agility in multiplatform distribution
Technologies used
The solution was designed using several AWS technologies, including:
AWS Services
Transcribe
Bedrock
S3
Lambda
DynamoDB
Cognito
Amplify
Languages, Libs and Frameworks
Python
Javascript
Node
React
Conclusion:
The implementation of this solution significantly transformed the client's ability to process and make available its journalistic content, establishing new standards of efficiency and quality in the Brazilian television market.
The project not only optimized operational processes, but also opened up new possibilities for monetizing and leveraging the broadcaster's rich journalistic collection.
For Gabriel Casara, CGO of BlueMetrics, this project once again demonstrates our company’s ability to develop solutions that bring real impacts to businesses. “This is a solution that has enormous potential for application in companies that generate large volumes of information, such as newspapers, radio stations, communication networks in general and content or streaming platforms, to name just a few examples.”
How about creating a case like this for your company? Let's schedule a call?
Discover some Use Cases .
About BlueMetrics
BlueMetrics was founded in 2016 and has already delivered more than 160 successful solutions in the areas of Data & Analytics, GenAI and Machine Learning for more than 70 companies in the United States, Brazil, Argentina, Colombia and Mexico. It has its own methodology and a multidisciplinary team focused on delivering solutions to real challenges in the business world.
Comments