FAQ

Yes. You can create a free account and start transcribing right away without a credit card. The homepage demo and documentation are also available before deeper setup.

You can upload audio directly in the product, use the browser upload flow for private files, or provide a remote URL through the API when the media is on a public HTTP/HTTPS host. Supported formats include MP3, WAV, FLAC, OGG, M4A, AAC, WMA, WEBM, and OPUS.

The current authentication flow supports email and Google sign-in, with a clear path back into the transcription flow after authentication.

Depending on the options enabled, Tuplets can return speaker diarization, PII processing, summaries, sentiment analysis, and structured analytics alongside the base transcript.

PII processing detects sensitive spans once on the full transcript and uses those same spans for transcript, segment, and premium word-level redaction. Structured identifiers like email, SSN, IP address, card numbers, and validated phone-like values are handled with deterministic checks, while names and address-like phrases use contextual entity detection. Generic organization and location names are excluded by default to reduce false positives. A final automated review pass checks the masked transcript for any surviving direct identifiers before the result is returned. PII currently runs only for English, Spanish, French, German, Portuguese, Italian, Dutch, and Polish (en, es, fr, de, pt, it, nl, pl). The mode is coverage-first, so short names and some ambiguous address-like text may still be masked when privacy is the safer choice. PII currently runs only for English, Spanish, French, German, Portuguese, Italian, Dutch, and Polish (en, es, fr, de, pt, it, nl, pl). If the transcript language resolves outside that set, PII is skipped and you are not charged for PII processing.

Tuplets standard transcription supports 96 languages, including English, Spanish, French, German, Chinese, Japanese, Korean, and Portuguese. Premium transcription supports a smaller 30-language set for harder audio and long-form recordings.

The maximum file size for all submission methods (direct upload, browser upload, and remote URL) is 1 GB. Audio must be at least 5 seconds and can be as long as 8 hours. WAV files are further limited by the 4 GiB container size of the RIFF format, and remote URLs must stay on public internet hosts even after redirects.

Yes. The documentation includes cURL, Python, and Node.js examples, sample responses, error handling guidance, pricing notes, and rate limit details.

API requests use a Bearer token in the Authorization header. Keys begin with tb_ and can be generated from dashboard settings.

Jobs are processed asynchronously. After submitting a job, you poll the status endpoint until completion and then download the transcript JSON, including timestamps, speaker labels, and optional analytics.