You are building transcription for thousands of hour-long sales calls per day. Lay out the audio front end: format and sample rate, how you chunk long recordings, how chunks are merged back, and how you keep throughput and accuracy acceptable.
Free · 2 AI evals / day
The pipeline has four stages: normalize, chunk, transcribe in parallel, stitch.
**Normalize.** Telephony stacks produce audio in various codecs (mu-law, Opus, MP3) at various sample rates (8 kHz to 48 kHz). Decode everything to the format the speech model expects: usually 16 kHz mono PCM. Avoid going through a low-bitrate lossy codec twice; consonants are the first thing compression eats.
**Chunk.** Speech models cap input length at 30 seconds to a few minutes. Cut the hour-long audio into chunks, but cut at silences found by voice activity detection rather than at fixed time marks. Add a 2 to 5 second overlap between consecutive chunks so words on the seam are not lost.
**Transcribe in parallel.** Chunks are independent, so fan them out across multiple workers or batch them on a single GPU. Throughput scales linearly with worker count.
**Stitch.** Reassemble transcripts in order, using word-level timestamps to drop duplicates in the overlap region. Add diarization as a separate pass if you need speaker labels. Track word error rate on a labeled set so regressions show up as metrics.
**Normalize first.** Decode whatever codec the telephony stack produces (mu-law, Opus, AMR, MP3) and resample to 16 kHz mono, the canonical input for Whisper, Deepgram Nova-3, AssemblyAI Universal, and Google Chirp 3. Keep a lossless or high-bitrate intermediate; double-pass lossy compression chews consonants.
**Chunk on silence with overlap.** Run voice activity detection to find low-energy regions and cut there. For continuous-speech regions that exceed the model window, force a cut and add a 2 to 5 second overlap. The overlap is small relative to a 30 to 60 second chunk but enough to preserve any boundary word with bilateral context.
**Stitch with timestamps.** Word-level timestamps from the model let you align overlapping transcripts and drop duplicates by picking the higher-confidence version. Without timestamps you cannot do this cleanly.
**Parallelize for throughput.** Chunks are independent: fan them out to a worker pool, batch them on GPU if you self-host, or use the provider's async batch API. Reassemble in chunk order at the end.
**Accuracy boosters.** Pass domain vocabulary (product names, competitor names, internal jargon) via prompt or boost lists. Run **diarization** as a separate stage (pyannote, Deepgram speakers, AssemblyAI speaker labels) if speaker turns matter; mixing diarization with transcription in a single model usually loses accuracy on both.
**Govern with WER.** Maintain a labeled set of real calls and measure word error rate end-to-end. Codec changes, model swaps, and VAD threshold changes all show up as WER deltas before they show up as customer complaints.
Quick reference
TL;DR
Resample to 16 kHz mono, chunk at VAD silences with a few seconds of overlap, fan out chunks to parallel workers, merge with word-level timestamps, and gate the pipeline on WER measured against labeled call samples.
Imagine a giant restaurant where every cook can only handle small plates. A whole roast lamb (the hour-long call) has to be carved before anyone can cook it. You first wash and trim the meat so everyone is working with the same starting condition (resample to 16 kHz mono). Then you carve at natural joints rather than chopping randomly, and you leave a little meat overlapping each slice so nothing is lost at the cuts (silence-based chunking with overlap). Each cook handles one slice in parallel (workers), and a plater reassembles the meal in the right order, removing the overlap so nothing is duplicated. A taster checks a few plates each day to make sure nothing has gone wrong.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example. Click to expand.
Everything you need to truly understand this topic: intuition, mechanics, step by step explanation, code, formulas, and worked example.
Real-time streaming transcription during a live call Streaming APIs handle chunking and overlap internally; the batch-pipeline shape does not apply
Very short audio clips (under the per-request length limit) Chunking adds latency for no benefit when a single call covers the whole clip
Audio where speaker labels do not matter and accuracy targets are modest Skipping diarization and tight VAD tuning saves engineering time; revisit only if downstream consumers ask for it
Quick scan · 2–4 min
Everything important, quickly.
6 minutes: normalization choices, VAD plus overlap chunking, parallel throughput math at thousands of calls per day, and the labeled WER eval that keeps regressions out of production.
Real-world examples
Real products, models, and research that use this idea.
1Gong and Chorus.ai both publish that production sales-call transcription resamples to 16 kHz mono and runs VAD before any model call
2Deepgram Nova-3 and AssemblyAI Universal both expose word-level timestamps explicitly so callers can stitch overlapping chunks
3pyannote.audio is the standard open-source diarization stage that runs alongside (not inside) a speech model
4OpenAI Whisper's reference implementation uses a 30-second window with overlap and ships VAD as a recommended preprocessing step
Interviewer follow-ups
What an interviewer would ask next. Try answering before peeking at the approach.
QHow would you decide between self-hosting Whisper on GPU vs using a managed API like Deepgram or AssemblyAI?
Sign in or go Pro to see the approach for this follow-up.
QWhat changes when the audio is in a less-resourced language?
Sign in or go Pro to see the approach for this follow-up.
Don't say this
Red flags and common mistakes that signal junior thinking. Click to expand.
Most common mistake
Sending raw telephony audio (mu-law 8 kHz) straight to a model trained on wideband audio, then cutting it at fixed time marks with no overlap or diarization plan.