Speech to text software for OBS creators
Drop in the recording. Get editable text.
For a saved OBS recording, upload the file to OpenWhispr and get editable note text. If you need captions while you stream, choose software built to update OBS live. Timed exports are available when the transcription includes timing information.
Downloaded by 150k+ users
After the recording is saved
Your stream is over. The spoken words are still trapped in the recording.
Turn the saved file into editable note text. Correct the words before you reuse them in a description, chapter list, post, or subtitle workflow.
Get the spoken words out of the recording.
Choose a saved audio or video file and turn its speech into an editable note. Keep the recording for playback while you work with words you can search, copy, and correct.
You still need words you can correct.
Edit the note before you quote it, publish it, or build a description from it.
A subtitle file needs timing, not just words.
OpenWhispr can save returned segments on the note. Without returned segments, the note still has editable text, but there is no transcript to export as timed SRT.
Free does not mean every route has every output.
Free includes unlimited local models and 2,000 OpenWhispr Cloud words each week. Start with the mode that fits the recording, then decide whether unlimited Cloud use is worth an upgrade.
What you get
A saved OBS recording, turned into text you can work with.
Choose Cloud when fast, consistent transcription and no local-model download matter. Choose local when offline or device-only processing matters. Both paths return text for the saved recording.
Cloud transcription without a local model download
Select a saved recording and choose OpenWhispr Cloud for high accuracy and speed across hardware. The audio is sent only to transcribe it, then immediately discarded.
Local processing for offline or device-only work
Select a local model when you need to transcribe a saved file without internet. The resulting note gives you editable text to review on your computer.
Keep plain text, or export returned timed segments
The uploaded recording becomes an editable note. When the selected transcription route returns segments, the note can export TXT, SRT, Markdown, or JSON after you choose a save location.
Saved-recording workflow
1 file
choose a saved audio or video file, then turn its speech into an editable note
Free local models
$0
unlimited local transcription is included on every plan
Free OpenWhispr Cloud allowance
2,000
words each week. Pro and Business include unlimited OpenWhispr Cloud transcription
How it works
Save the recording. Turn it into a note. Review what came back.
This post-recording workflow starts with a saved file. It ends with editable text, and can include a timed export when the transcription includes timing information.
Download for free.
OpenWhispr runs on Mac, Windows, and Linux. Free includes unlimited local models and 2,000 OpenWhispr Cloud words each week.
Upload the saved recording.
Choose the saved file, then choose local processing or OpenWhispr Cloud. The app transcribes it and saves the words as a note.
Edit the note. Export when timing is available.
Correct the saved note text. When the transcription includes timing information, choose where to save TXT, SRT, Markdown, or JSON.
No convincing needed
10 reasons OBS creators choose OpenWhispr after recording
These are the reasons to use OpenWhispr once you have a saved recording and need editable text, a careful review, or a conditional timed export.
Turn the recording into editable note text
Choose a saved file and OpenWhispr saves a successful transcription as a note. You get words you can revise instead of a recording you must replay to find a phrase.
The note is editable before it is reused
A successful upload saves its transcription as note text. Correct speaker names, stream jargon, or a bad phrase before you turn the words into a description, chapter list, or post.
Local transcription stays on the device
Choose local processing when you need an offline or device-only path for the saved recording. Local models are unlimited and included on every plan.
Cloud avoids a model download
Choose OpenWhispr Cloud when speed, accuracy, and consistent performance across hardware matter more than an offline path. Cloud audio is discarded after transcription.
Free starts with a real choice
Free includes unlimited local models, 2,000 OpenWhispr Cloud words each week, and 5 hours of meeting recordings a month. It is a starting point, not an unlimited Cloud plan.
Use timed export only when timing exists
When the transcription includes usable timing information, OpenWhispr stores it with the note and lets you export TXT, SRT, Markdown, or JSON. Text-only results still remain editable notes.
Save the note in the folder you choose
Choose a folder for the saved recording before you transcribe it. The finished note is saved there with its editable text, ready for the rest of your post-recording work.
Speaker labels are an upload option
You can opt into speaker detection for uploaded audio. It can help separate a conversation in the saved note, but you should still review the labels and wording.
Choose a size limit that fits the file
Local processing has no file-size restriction in the upload flow. OpenWhispr Cloud Free accepts files up to 25 MB, while Pro accepts files up to 500 MB.
Paid plans extend the Cloud workflow
Pro and Business include unlimited OpenWhispr Cloud transcription. Pro also adds 20 hours of meeting recordings a month, while Business includes unlimited meeting recordings.
Before you download
The questions OBS creators need answered first.
Straight answers on saved files, editable notes, timed exports, privacy, and the difference between free local models and paid Cloud use.
Does OpenWhispr provide live captions inside OBS?
What does it do with an OBS recording?
Can I get an SRT file from every uploaded recording?
Can I transcribe a saved recording offline?
What happens to Cloud audio?
What is free, and what needs a paid plan?
What users say
What OpenWhispr users say.
General OpenWhispr transcription feedback. The saved-recording workflow is described above.
Note
Saved-recording workflow
Upload a saved file, review the editable text, and export timed formats only when timing information is available.
Started using OpenWhispr with my local models and hardware. I have to say, this is better than typing.
I switched to voice input for my Claude Code chats. Even when I stumble and rephrase mid-sentence, the transcription comes out clean and polished.
I needed a local model for when I'm travelling or have no WiFi, and this perfectly solves it. The UI and performance are great.
Pricing
Free forever.
Upgrade when you want more.
FreePopular $0No card details needed | Pro $6.67/user/mo$80/user billed annually Start with Pro | Business $13.33/user/mo$160/user billed annually Start with Business | |
|---|---|---|---|
| Best for | Creators who want local transcription for saved recordings and a limited OpenWhispr Cloud allowance | Creators who want unlimited OpenWhispr Cloud transcription plus sync, mobile, and API/MCP access | Teams that need unlimited meeting recordings and chat over their saved notes and transcripts |
| Main reason to choose | Unlimited local models plus a limited OpenWhispr Cloud allowance for saved recordings | Unlimited OpenWhispr Cloud transcription plus mobile, sync, and API/MCP access | Unlimited meeting recordings plus chat over your notes and transcripts |
| Offline speech-to-textOffline speech-to-text runs entirely on your own device, it works without internet connection, and it's unlimited and free. | Included | Included | Included |
| Cloud speech-to-textCloud speech-to-text sends audio to OpenWhispr Cloud for the highest accuracy and speed, with no local models to download. | 2,000 words/week via OpenWhispr Cloud, or unlimited using your own API keys | Unlimited OpenWhispr Cloud speech-to-text | Unlimited OpenWhispr Cloud speech-to-text |
| Meeting recordings | 5 hours/month | 20 hours/month | Unlimited |
| Privacy & data handling | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. | Offline audio stays on your device. Cloud audio is sent only to transcribe it, then never stored. |
| Setup experience | Hands-on: install app, choose local models, optionally add API keys | Easy: install app, upgrade, use unlimited cloud speech-to-text | Moderate: configure users, Agent mode, and data workflows |
| Advanced features |
|
|
|
| Team management | None | None | Basic team / workflow use |
| Support | Community support | Email support | Priority support |
Need SSO, compliance features, admin controls, or dedicated support for a larger team?
We also offer a custom Enterprise plan with managed onboarding and tailored features.
Talk to us
Built in the open
The recording is only the first file in the workflow.
OpenWhispr gives a saved recording a practical next step: editable note text. Download it when that is the work you need to do next.
Choose Cloud for high-speed transcription without a local-model download, or choose a local model for device-only and offline processing. The free plan includes unlimited local models; paid plans extend OpenWhispr Cloud use and meeting-recording time.
The code is open source. If the upload or export workflow does not fit your recording, you can check the product behavior and ask the team in Discord.
Free · open source · local-first
Get the words out of the saved recording.
Download OpenWhispr to turn a saved recording into editable note text, then review and reuse the words.
Download for freeFree on Mac, Windows, and Linux.