Upload a session recording in parts
Choose a local MP3, WAV or M4A from a room recorder, or an MP4, MOV or WebM from an online session. Split longer sessions into parts of 10 minutes or less before uploading.

Focus group transcription turns a recorded group discussion into a source-language text draft with timestamps. Upload an audio or video recording of a session up to 10 minutes and 200 MiB, review the credit quote, then download TXT, SRT or VTT for your analysis.
Choose a file, then confirm to continue.
1 credit per started 30 seconds. Quote before running; failed runs release credits. No free transcription preview.

Upload a session you recorded with consent. You get timestamped segments in the spoken language to check against the recording, with text and subtitle downloads for your analysis workflow.

Use a focus group you recorded with participants' consent. Room recorders usually produce MP3, WAV or M4A; online sessions often export MP4. Each upload can be up to 10 minutes and 200 MiB, so split a full session into parts in an audio or video editor before uploading.
For audio files, see the Audio to Text hub; for session video, see Video to Text.
Focus groups are demanding recordings to transcribe: several people may talk over each other, react at once or speak away from the microphone. The transcript is a machine draft, not a proofread record, and it does not label speakers. Place the recorder centrally, ask people to speak one at a time, and plan time to review the draft against the audio.
For one-to-one research conversations, see Interview Transcription. For internal recorded calls, see Meeting Transcription. For recorded shows and panels, see Podcast Transcription.
Upload files up to 200 MiB and 10 minutes. Transcription costs 1 credit per started 30 seconds, with a minimum of 1 credit. Sign-in is required; review the measured duration and quote before starting. There is no free transcription preview.
Upload only sessions you have the rights and participants' consent to use. Review machine-generated words and timestamps before analysis. This mode does not translate, label speakers, summarize or include human proofreading. See pricing and the terms.
Choose a local MP3, WAV or M4A from a room recorder, or an MP4, MOV or WebM from an online session. Split longer sessions into parts of 10 minutes or less before uploading.

Read the timestamped segments in the spoken language. Re-listen where participants overlap or speak quietly, and correct product names, numbers and slang that recognition misheard.

Choose TXT to label participants, anonymize names and import into your qualitative analysis tool. Choose SRT or VTT to keep timestamps for clips and highlight reels.

UX researchers
Use the downloaded text as the starting point for affinity mapping or thematic coding after you review it.
Market researchers
Find quotations by timestamp and check them against the recording before they go into a report.
Academic research teams
Follow your ethics approval and data policy; remove identifying details from the downloaded text yourself.
Moderators
Use timestamps to jump to key moments while writing your own debrief. No summary is generated for you.
Split the recording into authorized parts within the size and duration limits. Choose a file and sign in to continue.
Check the duration-based credit quote and explicitly start transcription. There is no free transcription preview.
Read the recognized words in their original language. Download TXT, SRT or VTT, then add participant labels and correct errors in your editor.
Interview transcription for MP4, MOV, WebM, MP3, WAV or M4A up to 10 minutes and 200 MiB. Download TXT, SRT or VTT after reviewing the quote.
Meeting transcription after the call: upload an MP4 or M4A recording up to 10 minutes and 200 MiB, then download TXT, SRT or VTT. No meeting bot.
Convert audio to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Upload video up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
Podcast transcription for MP3, WAV or M4A up to 10 minutes and 200 MiB. Download TXT, SRT or VTT; sign in and review the credit quote first.
Translate a video into 13 languages with AI dubbing. Try a free 30-second voice preview (subject to account preview limits), then download video, audio and separate SRT/VTT subtitles.
Translate MP3, WAV or M4A into AI speech in 13 languages. Try a free 30-second preview (subject to account preview limits), then download audio and SRT/VTT subtitles online.
Translate UTF-8 SRT or VTT files up to 2 MiB into 1–5 languages. Download both formats with original timings, from 1 credit per minute per language.
Upload UTF-8 SRT up to 2 MiB, translate into 1–5 languages and download SRT with original timings. From 1 credit per minute per language; no video needed.
Upload video up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
Upload audio up to 10 minutes and 200 MiB. Transcribe at 1 credit per started 30 seconds; download SRT, VTT and TXT after reviewing the quote.
Convert MP3 to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Convert MP4 to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Convert MOV to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Convert M4A to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Convert WAV to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Convert WebM video to text online: up to 10 minutes and 200 MiB. Download TXT, SRT or VTT at 1 credit per started 30 seconds. No app; review the quote first.
Transcribe voice memos from iPhone M4A files up to 10 minutes and 200 MiB. Download TXT, SRT or VTT; sign in and review the credit quote first.
Sermon transcription for MP3, WAV or M4A up to 10 minutes and 200 MiB. Download text or subtitles; sign in and review the credit quote first.
Dub an MP4, MOV or WebM and burn the translated captions into the video, for up to 5 languages per run. Try a free 30-second preview, subject to account preview limits.
Translate podcast audio into AI speech in 13 languages, up to 5 per run. MP3, WAV or M4A up to 10 minutes. Optional voice cloning with consent; free 30-second preview.
Lecture transcription for MP4, MOV, WebM, MP3, WAV or M4A up to 10 minutes and 200 MiB per file. Download TXT, SRT or VTT after reviewing the quote.
Transcribe a recorded phone call from MP3, WAV or M4A up to 10 minutes and 200 MiB. Download TXT, SRT or VTT; we do not record or join calls.
AI lip sync for one front-facing speaker in videos up to 210 seconds. Preview the translated voice free for 30 seconds, subject to account preview limits, before full dubbing.
Bring a file you have permission to use. Review the quote before starting a paid run.
Upload a local audio or video recording of the session, sign in and review the measured duration and credit quote. Start transcription, then download TXT, SRT or VTT.
MP3, WAV and M4A audio or MP4, MOV and WebM video up to 200 MiB and 10 minutes. Both limits apply; split a full session into parts before uploading.
No. The transcript and downloads contain timestamps and recognized words without speaker names. Assign moderator and participant labels in your own document.
Accuracy follows recording quality. Several people talking at once, distant microphones and room noise cause more recognition errors, so review the draft against the recording.
No. The transcript is machine-generated and not proofread by a person. Review and correct it yourself before coding or quoting participants.
1 credit per started 30 seconds, with a minimum of 1 credit. A 10-minute part costs 20 credits; the quote appears before you start.
No. Transcription runs only after you accept the credit quote. The free dubbing preview does not apply to transcription mode.
No. The transcript stays in the automatically detected spoken language. This mode does not translate or summarize the session.
Yes. Upload only sessions you have the rights and participants' consent to transcribe, in line with your study's consent form and data policy.
No. Selecting and uploading a file do not start paid recognition. Review the measured duration and credit quote, then explicitly start transcription.
Choose your file, sign in and continue in the workspace. You decide when processing starts.