Offline dictation, audio transcription, and meeting notes with on-device Whisper and NVIDIA Parakeet models. Private voice workflow for Mac & Linux with optional AI summaries.

ElevenAgents by ElevenLabs — Scale conversations without scaling your team

Scale conversations without scaling your team

Hey there! 👋 Just wanted to share something cool I've been working on called VoxBee. I originally built it because I wanted a private, local speech-to-text app without any subscriptions. But as more people used it, I realized folks wanted other audio features too, all while keeping things local and private (or using optional local/cloud AI for more advanced stuff). So, VoxBee is now an all-in-one audio platform! You can: * Do offline dictation with Whisper and Parakeet. * Transcribe and summarize any audio/video using Ollama or cloud models. * Automatically record, transcribe, and summarize meeting audio. * Dictate into a scratchpad and then transform it with AI – think turning voice notes into emails, meeting notes, to-do lists, blog posts, and more with 8 built-in templates! * And lots more to come! A key thing is that everything, from meeting notes to transcriptions, saves as markdown files right on your device. This means you can easily use your own AI agents with them and integrate into your other workflows. Give it a try – it's free for 14 days! I'd love to hear your feedback and any feature requests you have. 😊

The voice action is really fast, and I've been able to be more productive when I can speak my thoughts instead of typing (brainstorming a doc, an email, a message to a colleague, etc.). It's also super work-friendly because the dictation never leaves the local device and is never shared with a server or third party.

I also use the screenshot capture feature often when vibe coding. I can easily take a screenshot, dictate it, and paste it into the chat (in any vibe coding tool I am using).

I would also want a mobile app because it is hard to type long texts and emails on a phone.

Sometimes, it does not work well with external microphones. I would like to use external headphones so I can listen to music and dictate at the same time.

I chose Voxbee over Wisper Flow because of its one-time pricing model rather than a subscription. It's quite affordable at a $40 one-time fee.

I also like that my dictation is never stored on a server or shared with anyone or anything other than my personal local device.

ElevenAgents by ElevenLabs — Scale conversations without scaling your team

Scale conversations without scaling your team

I also use the screenshot capture feature often when vibe coding. I can easily take a screenshot, dictate it, and paste it into the chat (in any vibe coding tool I am using).

I would also want a mobile app because it is hard to type long texts and emails on a phone.

Sometimes, it does not work well with external microphones. I would like to use external headphones so I can listen to music and dictate at the same time.

I chose Voxbee over Wisper Flow because of its one-time pricing model rather than a subscription. It's quite affordable at a $40 one-time fee.

I also like that my dictation is never stored on a server or shared with anyone or anything other than my personal local device.

VoxBee

Dictation. Transcription. Meeting recording - all in one!

Dictation. Transcription. Meeting recording - all in one!

What's great

What needs improvement

vs Alternatives

What's great

What needs improvement

vs Alternatives