Play any long AI-narrated audiobook and sooner or later you hit it. The narrator finishes a paragraph, starts the next one, and sounds like a slightly different person. Same voice on paper. But the pitch moved, the energy reset, the read changed. We call these moments seams, and after months of producing scored audiobooks at Lex, we consider them the hardest quality problem in AI audio.

This post covers what causes seams, how to measure them, and the pipeline we built to get rid of them.

Key numbers: listeners start noticing a pitch jump around 20 Hz. Raw chunk joins in our tests drifted 30–48 Hz (most of a semitone). With request stitching plus our take-selection pipeline, every join held within 15 Hz and most landed in single digits.

Every chunk is a cold start

Text-to-speech APIs cap the amount of text per request, usually at a few thousand characters. A 20-minute chapter runs past 15,000 characters, so producing one means five to ten separate requests joined into a single file.

Most current TTS models are stateless. A request knows nothing about the audio generated before it. The model is not continuing a performance; it starts a new one each time, and it improvises the narrator's register from scratch. Two improvisations rarely land in the same place.

The drift is measurable. We check every join by comparing speech level and median pitch in a four-second window on each side. On a typical narrator, a pitch jump above about 20 Hz is where listeners start to notice. Raw chunk joins, with no mitigation, gave us jumps of 30 to 48 Hz in our tests. That is most of a semitone. The narrator is changing key in the middle of a paragraph.

What actually reduces seams

Practice lead-ins

Each chunk after the first is rendered with the previous chunk's last two sentences prepended. The model reads them, settles into the voice, then reaches the text we keep. The practice audio is trimmed off afterward using the word-level alignment. This removes the worst cold-start artifact, where the first line after a join comes in harsh.

Multiple takes, scored for continuity

For chunks that sit against a seam we render up to three takes and score each against the audio it has to follow, using the same level and pitch measurements as our QA. The closest take wins. This is the highest-leverage step in the stack. A take that lands 40 Hz hot costs nothing if another take landed at 5.

Level matching

Every take rolls its own overall loudness. Before joining, the incoming take is gain-adjusted to match the speech level of the audio before it. Two dB of mismatch reads as an edit. Corrected, it reads as a sentence break.

Room tone instead of crossfades

Crossfading two vocal takes smears them together and sounds like what it is. We butt-join across a 380 ms pause instead, and we fill that pause with room tone extracted from the incoming take. Pure digital silence between two voiced takes is audible as a hole in the recording. Room tone reads as a breath.

Surgical splices

After the render, a QA pass scans every join. Anything still flagged gets fixed in isolation. We re-render just the offending passage, sandwiched between its surrounding sentences so the model performs it in context, pick the most continuous of several takes, and splice it in. The rest of the chapter is untouched.

Request stitching

Some models support request stitching. You pass the previous chunk's text and request IDs with each call, and the model conditions its new take on what came before. We ran the same chapter both ways. Without stitching, joins drifted up to 48 Hz. With it, every join held within 15 Hz and most were in single digits, below the threshold where anyone notices.

The complication, as of mid-2026, is that the newest and most expressive models do not support stitching yet, while the models that stitch read flatter. So we render the base narration on a stitching model for continuity, and splice in the expressive model line by line where a delivery needs it, like a whispered prophecy or an urgent aside. Two models, one narrator.

Measure it, because your ears adapt

You cannot QA seams by listening alone. By the third chapter of a session you stop hearing drift that a fresh listener notices immediately. Every join in every chapter we ship goes through the same objective gate, and the seam map is stored alongside the audio so later edits know where the fragile points are.

Mastering engineers have worked this way for decades. AI narration does not get to skip the discipline.

Lex produces fully scored AI audiobooks, with narration, music, ambience and sound effects, for classic literature and original works. Hear finished productions on our audio showcase or in the free app.