VoxLingo transcription FAQ

Choose a file or drag it onto the upload area. Uploading starts when you are signed in with available transcription time or eligible for a guest trial. After uploading, choose the spoken language, optionally enable speaker labels or add vocabulary hints, and select Start transcription. Open the result in the same workspace when it is ready.

When a guest trial is available, an eligible visitor can try one recording of up to 120 seconds without an account. Your browser prepares the beginning of the recording locally and uploads only that clip. Eligibility and service limits apply. Trial results support playback, copying and TXT download; longer recordings and other exports require an account and available transcription time.

VoxLingo accepts AAC, AIFF, AMR, ASF, FLAC, MP3, OGG, WAV, WebM, M4A, and MP4, as listed by Soniox for file transcription. A video must contain a decodable audio track. Soniox supports up to 300 minutes (5 hours) per transcription. VoxLingo currently limits full-file uploads to 1 GiB (1,073,741,824 bytes); this is a site safeguard, not a published Soniox per-file size limit. For full transcription, the browser copies the audio track from a video when possible and uploads that audio. Otherwise, it uploads the original video. The size limit applies to the file sent for upload. You also need enough available transcription time.

Guest trials also require a format and audio codec that your browser can decode locally. AIFF, AMR and ASF cannot currently be prepared for a trial; sign in with available transcription time to upload those files, or use another format. Other formats are checked in your browser. The original trial source can be up to 2 GiB, but only the first 120 seconds are converted into a short WAV and uploaded. If preparation fails, the original file is not uploaded.

VoxLingo supports the 60 languages listed by the Soniox transcription model. Leave Audio language set to Detect automatically, or choose an expected language to guide recognition. A language hint does not prevent other supported languages from appearing in the transcript.

Select Record audio, allow microphone access and choose your microphone and language. You can pause and resume. End and transcribe saves the recording and sends it through the same upload and transcription process. Text appears after processing the saved recording; the web tool does not display speech as you speak.

Transcription uses cloud recognition services. Your uploaded recording and transcript content are stored privately in cloud storage, and access through VoxLingo is checked against your account or guest session. For a guest trial, only preparation of the short clip happens in your browser; the clip is then uploaded for recognition.

Guest recordings and results remain accessible for 24 hours after transcription completes, then access expires and background cleanup starts. Sign in before expiry to save the result to your web account without repeating transcription. Saved account results are no longer subject to the guest 24-hour expiry and remain available for later review and deletion.

Open a completed transcript to review the text alongside playback and timestamps. Signed-in users can edit the text, title and speaker names, then export TXT, SRT, VTT, and DOCX. Edits are saved to your web account once saving is confirmed. Guest trial results support copying and TXT download. Check names, numbers and subtitle timing before sharing an export.

Time is reserved when you start a transcription and settled using the actual recognized audio duration. Confirmed failures that did not complete recognition release the reservation. Requests with an uncertain processing state are checked before the balance is finalized. For multiple files, each is processed separately; files without enough available time remain waiting.

Weekly and monthly plans provide time for each billing period. Yearly plans are paid annually and release their included time in monthly windows, rather than all at once. Unused time does not roll over. Subscriptions renew automatically. Use Manage subscription in your billing page to cancel future renewal in Stripe; cancellation takes effect at the end of the paid billing period. View transcription plans.

Deletion immediately removes access through VoxLingo and starts background cleanup of the recording and transcript files. It is permanent, with no recycle bin. Previously issued playback links can remain usable until they expire, and cleanup can take additional time if a service needs to retry. Minimal usage and billing records are retained for reconciliation. Recognition already in progress is still settled.

Web and iPhone accounts, subscriptions and transcripts are separate. An iPhone subscription does not provide web transcription time, and a web subscription does not unlock the iPhone app. The iPhone app focuses on live voice, conversation, photo and document translation; the web tool focuses on saved audio and video transcription. Get VoxLingo for iPhone.