Re-transcribe a Call with Whisper (Fallback Transcription)

When to use this

Your call recordings are automatically transcribed by our voice provider as the call happens. Most of the time that transcript is what you read on the conversation page. Occasionally — for reasons that are usually a quirk of the underlying audio, not the call itself — the automatic transcript drops part of the conversation: a missing turn here, a long silent gap that wasn’t actually silent, a name spelled three different ways.

When that happens, you can run a fallback transcription using a different speech-recognition engine on the same audio. It appears alongside the original — the original is never modified — so you can compare and decide which to trust.

This is a stopgap. The primary transcript is still the one created by the voice provider during the call.

How to run it

1. Open the conversation you want to re-transcribe.
2. In the transcript section, look for the Re-transcribe (Whisper) button.
   • If you don’t see the button, the feature isn’t enabled on your account. Reach out to your account contact at TriLuna.
3. Click it and accept the confirmation pop-up.
4. Wait. Re-transcription runs in the background — you can leave the page and come back. See How long it takes.
5. When it finishes, an amber panel appears above the original transcript with the Whisper version. Both stay visible.

Starting a re-transcription while one is already running on the same call won’t start a second one — you’ll be shown the run already in progress.

How long it takes

Roughly as long as the call itself. A 10-minute call takes about 10 minutes; a 45-minute call takes about 45. If someone else’s re-transcription is already running, yours waits its turn behind it.

That’s slower than it used to be, and it’s the deliberate trade for the section below: transcription now runs on TriLuna’s own hardware rather than a paid external service.

The page watches for the result for a while, but you don’t need to keep it open — the result is saved either way. If you leave, just reload the conversation later.

Cost

None. Re-transcription runs on TriLuna’s own hardware, so there’s no per-minute charge, and no limit on how many times you run it.

This changed in August 2026. Previously this feature called a paid external API and cost about $0.006 per minute of audio; older re-transcriptions in your account may still show a cost from when they were run.

What you’ll see

The Whisper panel shows:

• The engine that produced it (for example local-whisper)
• A timestamp of when the re-transcription completed
• Each spoken segment with a timestamp, in order

The whole call is transcribed, however long it is. (Earlier versions of this guide described a 24-minute limit, and before that long calls really were trimmed. Neither is true any more — long audio is processed in full.)

What the Whisper transcript is good at

• Catching turns the original transcript missed entirely
• Filling in mid-conversation gaps
• Picking up softer audio that the primary provider’s voice-activity detection skipped

What it isn’t good at

• Speaker labels. On a phone call, Whisper doesn’t know which voice is the agent and which is the caller. The panel shows what was said and when, but not who said it. The original transcript still has speaker labels — use both together when speaker identity matters. (Video meeting recordings are different: those do get speaker separation, labelled “Speaker 1”, “Speaker 2” and so on.)
• Names and unusual words. Like all general-purpose speech recognition, Whisper sometimes guesses wrong on proper names, company names, and domain jargon. Confirm against the original transcript.

Downloading both transcripts

The Download JSON button on the conversation page includes both transcripts when a Whisper re-transcription exists:

• whisper_rerun — the Whisper version: text, timestamped segments, plus provider, completed_at, audio_duration_secs and cost_cents (0 for runs on our own hardware)
• transcript — the original transcript, unchanged

If no Whisper re-transcription has been run for that call, only transcript is included.

Why is this a fallback and not the default?

The primary transcript is created by the same provider that handles the live call, so it benefits from context the audio file alone doesn’t carry (turn boundaries, agent vs. caller separation, real-time adjustments). When it works well — which is most of the time — it’s better than Whisper. Whisper is here for when it doesn’t.

Questions

If you keep seeing incomplete transcripts on calls where Whisper recovers the missing parts cleanly, tell us — that’s the signal we use to push for an upstream fix and decide whether to widen access to this feature.