Two Time Scales for Audio: Model Requests and Searchable Moments
Our audio pipeline used 10-minute model requests and 60-to-120-second retrieval fragments, with stored segments allowing reindexing without another speech call
Technically reviewed by Victor Sineglazov on .
We needed two different ways to divide an audio source. A speech-model request needed a manageable piece with its own retry state. Retrieval needed a shorter passage that could answer a question and point back to a useful moment. Using the same boundary for both would have coupled search quality to the mechanics of a paid model call.
Our October audio-source design separated those units. It targeted roughly 10-minute pieces for transcription and one-to-two-minute fragments for retrieval. Between them, the database stored timestamped transcript segments. That intermediate representation let us rebuild search fragments without paying to transcribe the recording again.
The first cut bounded the transcription job
The audio cutter returned each piece's ordinal, start and end in milliseconds, plus its temporary file path. The production implementation invoked ffmpeg with an argument list through a process builder. Tests used a separate cutter that could generate WAV pieces without requiring ffmpeg.
The recorded cutting rule looked for a suitable pause between 8 and 12 minutes from the piece start, targeting 10 minutes. It chose the midpoint of the longest detected pause in that window. If there was no pause, it cut at 12 minutes. The silence-detection settings used a threshold of -35 dB and a minimum pause of 0.4 seconds.
Each piece was encoded as mono OGG audio at 16 kHz and 32 kbps. These were settings in our historical integration, not a universal prescription for medical speech recognition. Their purpose here was to define the request unit separately from the eventual search passage.
Transcript segments joined the two time scales
The speech adapter returned segments with times relative to the beginning of the submitted piece. Stored transcript segments included the piece's offset, so their timestamps addressed the original recording. Forgetting that offset would send a citation from a later piece back toward the beginning of the source.
| Unit | Recorded boundary | Primary purpose |
|---|---|---|
| Transcription piece | Target 10 minutes; choose a pause in the 8 to 12 minute window | Bound a model request and its retries |
| Transcript segment | Model-provided interval translated to recording time | Store text and timing independently of search fragmentation |
| Retrieval fragment | At least 60 seconds, with a cut no later than 120 seconds | Return a shorter searchable passage and source interval |
The search chunker accumulated segments until it had at least 60 seconds. It then sought the longest intersegment pause of at least 0.6 seconds within the 120-second limit, with a forced cut at that limit. It concatenated the segment text without an added heading or overlap. The fragment's interval came from the first segment's start and the last segment's end.
A retry belonged to a piece, not the whole recording

Each piece had persistent work state. A worker claimed waiting work, called the model and committed the returned segments together with the completed piece state. Failed pieces could retry without discarding already completed transcription work. Restart recovery returned interrupted work to the waiting state.
When the final piece completed, the source version returned to the ordinary indexing pipeline. That next pass built retrieval fragments from database segments. It did not submit the recording to the speech model again. The late implementation notes also describe locking the version row around final completion so concurrent workers did not lose the transition.
This separation gave "reindex" a precise meaning. It rebuilt embeddings and fragment boundaries from stored text. "Transcribe again" was a different, explicit operation that replaced segment content as pieces completed. The latter could overwrite human corrections, so it needed a visible product warning.
Review approval was another independent boundary
When transcript review was required, the pipeline could finish indexing the version while withholding transcript points from search until approval. An indexed status alone therefore did not establish that transcript text was searchable. The administration view needed to explain the wait.
Approval or correction requested a rebuild from stored segments. It did not require another speech-model call. The design recorded a rebuild-request timestamp so a correction arriving during a rebuild could trigger another pass rather than disappear behind the worker's earlier read.
The resulting fragment also carried whether its text was model-written. This provenance flag did not measure transcription accuracy. Our separate account of errors hidden by a low word error rate addresses why source timing and review still matter when an aggregate metric looks reassuring.
Small configuration errors could multiply model calls
A late correction required explicit minimum durations for the piece target and retrieval-chunk minimum. The implementation notes describe the danger of a missing time unit being interpreted as milliseconds, creating thousands of paid calls. Startup validation was preferable to discovering that interpretation after work had entered the queue.
For verification, the design used the speech audit trail to distinguish operations: transcription produced a model-call record, while reindexing from stored segments should produce none. That is an observable cost boundary. It says nothing by itself about whether the transcript accurately preserves a clinically important number or unit.
Keeping the request piece, transcript segment and retrieval fragment separate let each change for its own reason. A retry could revisit one paid request, an editor could correct stored text and retrieval could rebuild shorter passages. The citation still needed to land on the original recording's timeline.
Evidence scope: the October 6 audio-source specification and its later implementation corrections. This account describes the recorded pipeline and configuration rules; it does not report a new speech-quality benchmark or a current provider recommendation.
FAQ
Quick answers to common questions about custom software development, pricing, process and technology.
Type to filter questions and answers. Use Topic to narrow the list.
Showing all 14
No matches
Try a different keyword, change the topic or clear filters
-
How long have you been in business?
Pharos Production has been in business since 2013, with over 13 years of experience in custom software development. During this time, we have delivered over 110 applications for 200+ clients across 28 industries, including FinTech, healthcare, crypto and e-commerce. We are rated 5/5 on Clutch based on 107 verified reviews (2026).
-
What services do you provide?
Pharos Production provides six core service categories: AI Development (LLM applications, AI agents, machine learning and computer vision), Blockchain and Web3 (smart contracts, DeFi, tokenization on Ethereum, Solana, TON and other chains), FinTech Development (payment platforms, digital banking, KYC and AML integration), Software Development (mobile apps, web platforms, database design, UI/UX), Security and QA (code audits, penetration testing, smart contract audits, manual and automated testing) and Consulting (architecture design, MVP validation, startup consulting).
-
Where is Pharos Production located?
Pharos Production is headquartered in Las Vegas, Nevada, USA (5348 Vegas Dr, Las Vegas, NV 89108), with an engineering office in Kyiv, Ukraine (44-B Eugene Konovalets Str. Suite 201, Kyiv 01133). We work with clients worldwide and provide remote collaboration across all time zones. Visit our contact page for directions and scheduling options.
-
How big is your team?
Pharos Production has a team of 90+ engineers, including software developers, blockchain specialists, QA engineers, DevOps experts, UI/UX designers, project managers and solution architects. Our founder, Dr. Dmytro Nasyrov, holds a PhD in Artificial Intelligence and leads the technical direction of all projects.
-
What types of customers do you serve?
We serve a wide range of clients, from startups and product companies to mid-sized enterprises and large institutions. Our clients include crypto exchanges, FinTech providers (like Pleenk), healthcare organizations, sportsbook operators (like Pro Gambling), e-commerce platforms and SaaS companies. Pharos Production has worked with 200+ clients across 28 industries since 2013, adapting engagement models to match each client's stage, whether it is MVP validation for a startup or enterprise-scale development for an established business.
-
How is a custom software development company different from an agency?
A custom software development company like Pharos Production assigns one dedicated engineering team that owns your product across multiple release cycles, instead of handing it off once a contract ends. Agencies more often rotate staff between clients and optimize for fast delivery over long-term product ownership.
Pharos Production keeps the same team on your codebase through 2-week sprints, so there is no re-onboarding cost each time you request a new feature.
-
How much does custom software development cost?
Custom software development costs vary based on project scope and complexity. At Pharos Production, typical project ranges are: MVP development ($10,000-$25,000), suitable for startups validating a product idea; full-fledged production ($25,000-$50,000), for established businesses scaling a proven concept; and full-cycle development ($50,000-$80,000+), for complex enterprise-grade systems. These ranges include architecture design, development, QA testing and deployment. Hourly rates range from $50 to $99 depending on role and seniority. Final pricing depends on technology stack, number of integrations and engagement model (staff augmentation, dedicated team or project outsourcing).
-
How long does it take to develop a custom software application?
Development timelines depend on scope and complexity. At Pharos Production, a typical MVP takes 2-4 months, a production-ready application takes 4-8 months and a complex enterprise system can take 8-12+ months. We use an agile methodology with 2-week sprints, delivering working increments after each sprint. Every sprint includes a retrospective, progress report and planning session for the next iteration. This approach ensures transparency and allows businesses to launch faster by prioritizing high-impact features first. Get a timeline estimate for your project.
-
What industries does Pharos Production serve?
Pharos Production serves 28 industries: FinTech, MiCA Compliance, Banking, Insurance, Crypto, Healthcare, Fitness, E-Commerce, Food & Restaurant, On-Demand, Manufacturing, Automotive, Energy, Oil & Gas, Supply Chain, Construction, Real Estate, Gaming, Streaming, Media, Telecom, Education, Aviation, Travel, Logistics, Marketing, Agriculture and Recommender Systems. Our deepest expertise is in FinTech, blockchain and healthcare, where we have delivered compliance-ready platforms (HIPAA, PCI DSS, GDPR) and high-load systems handling thousands of concurrent users. For the latest industry insights, read our guides on FinTech trends in 2026 and the Web3 technology stack.
-
Why hire a software development company instead of building in-house?
Hiring a software development company offers faster time-to-market, lower upfront costs and access to specialized expertise without long-term employment commitments. According to Deloitte's 2024 Global Outsourcing Survey, 57% of companies outsource software development to access skills they cannot hire internally.
Factor In-house team Software development company Time to assemble 3-6 months (recruiting + onboarding) 1-2 weeks Upfront cost High (salaries, benefits, equipment) Lower (project-based pricing) Specialized expertise Limited to who you can hire locally Access to 90+ engineers across blockchain, AI, FinTech Scalability Slow (each new hire takes months) Fast (scale up or down per sprint) Long-term commitment Full-time employment contracts Flexible engagement models Risk High if key engineers leave Company ensures continuity and knowledge transfer For businesses that need blockchain, AI or high-load architecture expertise, outsourcing to a specialized firm like Pharos Production reduces risk and accelerates delivery.
-
What projects does Pharos Production not take on?
Pharos Production focuses on mid-to-large custom software projects with budgets starting at $10,000. We do not take on template-based websites, WordPress theme customization or short-term contracts under one month. We also do not provide non-technical staffing (marketing, sales or design-only roles). Our strongest fit is blockchain, FinTech and healthcare projects where security, compliance and high-load architecture are critical. For smaller projects or MVPs under $10,000, we recommend exploring freelance platforms or no-code tools as a more cost-effective starting point.
-
Why does Pharos Production use agile methodology?
We use agile with 2-week sprints because it reduces the risk of building features that miss the mark. Each sprint ends with a working demo, a retrospective and a plan for the next iteration.
This means clients see progress every 14 days and can adjust priorities based on real results, not assumptions. We chose this approach after years of experience showing that rigid, fixed-scope contracts lead to scope creep, missed deadlines and products that do not match market needs by launch day.
-
When should you NOT hire a custom software development company?
Custom development is not the right choice in every situation. You should not hire a custom software company if: your problem is fully solved by an existing SaaS product (e.g. Shopify for e-commerce, Salesforce for CRM); your budget is under $10,000 and timeline is under 4 weeks; you need a simple landing page or marketing website (WordPress or Webflow is faster and cheaper); or you are still validating the idea and have not spoken to potential users yet.
In these cases, off-the-shelf tools or no-code platforms offer better ROI. Custom development makes sense when you need unique workflows, regulatory compliance, high-load architecture or competitive differentiation that packaged software cannot provide.
-
What kind of projects has Pharos Production delivered?
Here are three anonymized examples from our recent delivery history:
FinTech startup - payment platform (MVP)
Scope: mobile app + backend API with bank-grade encryption. Team: 4 engineers, 1 QA. Timeline: 10 weeks. Budget: $38,000. Result: launched on schedule, processed $2M+ in transactions within the first quarter.Healthcare provider - patient portal (Full product)
Scope: HIPAA-aligned web platform with EHR integration, appointment scheduling and telemedicine. Team: 6 engineers, 1 DevOps, 2 QA. Timeline: 6 months. Budget: $120,000. Result: 15,000+ active patients, zero compliance violations in two annual audits.Crypto exchange - trading engine (Complex)
Scope: high-load matching engine handling 50,000+ orders per second, multi-chain wallet infrastructure on Ethereum and Solana. Team: 8 engineers, 2 QA, 1 security auditor. Timeline: 11 months. Budget: $340,000. Result: 99.97% uptime, passed three independent security audits.See more projects: NoMoreBets, Pulse, Sagas, Gambit Stream and Pleenk. For the full portfolio, visit our case studies. Learn more about the technology behind these projects in our guide to stablecoins and crypto infrastructure.
Dmytro Ihnatov is the Lead Backend Developer at Pharos Production. He documents backend architecture and research experiments from the team's work on a professional learning platform for aesthetic medicine.