Upload Your Data: Existing Interviews, Audio, Video, and Transcripts

You don't have to collect your data on Qualz.ai to use Qualz.ai. If you've already run interviews — whether as recorded calls, video sessions, or written transcripts from another tool — you can upload them directly and run all of Qualz's AI analysis (transcription, multi-lens analysis, thematic synthesis, sentiment, etc.) on your existing material.

This guide covers where to find Upload Your Data, what you can upload, supported formats, size and batch limits, entitlement usage, and the typical bring-your-own-data flow.

Why upload your own data?

• You already have a corpus of interviews from a previous study and want to run multi-lens analysis on it.
• Your team uses another tool for recording (Zoom, Teams, Riverside, Otter, etc.) and wants Qualz purely for transcription + analysis.
• You have written transcripts (Word docs, PDFs) from manual or third-party transcription and want to consolidate them in one workspace.
• You ran a focus group, ethnographic session, or sales call you want to analyze qualitatively.

What you can upload

Qualz supports three upload modes:

1. Audio recordings

Upload existing audio files. Qualz transcribes them and produces a fully-aligned transcript with speaker labels, then makes them available for analysis.

• Supported formats: .mp3, .mpeg, .wav, .ogg, .m4a, .flac, .aac
• Recommended: mono or stereo, 16 kHz or higher sample rate, single speaker per channel when possible

2. Video recordings

Upload existing video files. Qualz extracts the audio, transcribes it, and lets you review the transcript alongside the video.

• Supported formats: .mp4, .webm, .avi, .mov, .mkv
• The video file itself is preserved so you can re-watch sessions inside the dashboard

3. Text transcripts

Already have a transcript from another tool? Upload it directly — no transcription pass needed.

• Supported formats: .txt, .doc, .docx, .pdf
• Speaker labels (e.g., Interviewer:, Participant:) are preserved when present
• Timestamps are optional

File size and length guidance

• Per-file size: text files can be up to 50 MB, audio files up to 500 MB, and video files up to 2 GB.
• Duration: there is no hard cap on interview length, but very long sessions (>3 hours) are best uploaded as separate parts when possible — it speeds up transcription, gives you finer control over redaction, and produces cleaner derived transcripts.
• Batch uploads: you can queue up to 20 text files, 10 audio files, or 10 video files in a single upload batch. Larger archives can be uploaded in multiple batches.

The upload flow

1. From the dashboard, open Interviews and click Upload Your Data. You can also open an existing interview study and upload from the transcript/upload area.
2. Drag and drop the file(s), or use the file picker.
3. Configure the optional settings:
   • Language — choose the source language for transcription/processing.
   • PII redaction at upload — apply redaction in a single pass before downstream analysis (see Transcript Workflows).
4. Submit. Audio/video uploads are transcribed in the background; text transcripts skip media transcription but still process before appearing in the transcript list.
5. Once processed, the transcript appears in your transcript list with the same actions as natively-collected interviews — analyze, run lens analyses, run transcript workflows (translation, redaction, enhancement), or share/export.

What it costs

Each uploaded file consumes 1 Transcription Upload entitlement from your workspace allocation. Audio/video that needs transcription and text-only uploads both count the same way. Subsequent analysis (multi-lens, thematic) consumes Analysis Units.

If you're not sure how much capacity your current allocations cover, see What are Entitlements? and How Entitlements Work. To expand capacity for a large historical archive, see How to Add Member Seats, Workspaces, or More Entitlements.

Tips for high-quality uploads

• Audio quality matters. Cleaner source audio yields better transcripts. If a file was recorded over a noisy line, run Enhance Transcription afterward (see Transcript Workflows).
• Use consistent speaker labels. If you upload pre-existing transcripts, normalize speaker labels (Interviewer, Participant 1, Participant 2) before upload — this makes downstream analysis cleaner.
• Strip identifying details if needed. If your transcripts contain PII, run PII redaction at upload instead of redacting after the fact, so derived analysis artifacts never see the raw values.
• Upload first, organize later. You can upload everything for a project in one batch and then group, tag, or filter from the transcript panel.

Bringing in survey data instead?

If your existing data is survey responses (quant + open-ended) rather than interview transcripts, see Upload and Analyze Your Existing Survey Data.

Related Guides

• Transcript Workflows: Translation, Redaction & Enhancement — Post-process uploaded transcripts
• How to Analyze Interview Data — Run multi-lens analysis on uploaded transcripts
• Managing Interview Sessions & Recordings — Organize uploaded sessions in your study