A free to use real-time audio transcription app for spontaneous speech

Transcribe audio to text in English, Finnish, Swedish, Estonian and Russian language. 20 h for free.

Sign up!

Already using Speaker? Log in

What is the Speaker transcription app?

Speaker by Feelingstream is a free to use real-time audio transcription app for spontaneous speech that helps to convert your interviews, lectures, meetings and other audio files to readable text.

Which languages can I transcribe in the Speaker app?

Today you can transcribe your speech in English, Swedish, Finnish, Estonian, Russian, Norwegian, Deutsch. Additional languages will be added over time.

Why should I choose the Speaker app?

  • Our own Feelingstream ASR models
  • Real-time transcription with only 200 ms delay
  • Transcription accuracy 80%+
  • Transcription model specially trained for spontaneous speech
  • Speech to text transcription in English, Swedish, Finnish, Estonian, Russian, Norwegian, Deutsch
  • Punctuation and capitalization
  • Data is secured
  • Easy to use

How is my data secured on Speaker app?

Please note that Feelingstream respects your privacy and guarantees that the data stored in the Service is used only in accordance with your will. Feelingstream also is dedicated to keeping your information secure. Feelingstream has implemented and will continue to employ commercially reasonable measures to ensure that data is processed securely and in compliance with applicable law.

You are obligated to keep your password confidential and not to disclose it to third parties. Feelingstream is not liable for your failure to keep your password or account details secure and confidential.

Please read more about data security and other topics in our Terms of Service and Privacy Policy.

Can I use the Speaker transcription app for free?

Yes! Sign up for a 20-hour free trial. You can buy additional transcription time based on your needs - either 10 hours or 50 hours. No hidden fees.

What is real-time transcription?

You can open the transcription app on your mobile phone, laptop, or tablet and start the transcription process. Choose the language and simply speak or record someone speaking as you need it. The automated speech recognition model then takes the audio and transcribes the words into text as you speak. There is a very slight delay (200ms) and you will see the words you’ve spoken transcribed on-screen. You can save the transcription for later use.

How can I use Speaker app for business use?

There are different use cases for businesses. You can transcribe your interviews, meetings, research notes, voice memos – you name it. If you wish to use the Speaker on a larger scale in your business, meaning that you want more than an account or two and may need a special setup, let us know at info@feelingstream.ai

Read more from our Business page.

How can I do transcription on my phone?

Open the Speaker app on the website https://speaker.feelingstream.com/

Log in to your account, choose the language for your transcription, then start transcribing. Save the transcription when you’re done. Available for use via your internet browser on both Iphone and Android.

How do I transcribe live meetings?

For transcribing live meetings, you can either use your mobile, tablet or laptop. Please place the device as close to the speaker as possible, as the transcription accuracy is affected by background noise and the microphone’s quality. Choose the correct language and just press start.

How do I transcribe online meetings?

If you have an online meeting using meeting software on your computer, it is possible to transcribe the text during the meeting. If you are using a laptop and the audio is coming from the speakers, your computer microphone will most likely pick up the audio with quite good quality for transcription. Start the transcription at the beginning of the meeting and save it for later. You can use the transcription for your meeting notes or for future use as a memo.

How can the speech to text Speaker app help people with hearing impairments?

As the Speaker app by Feelingstream is focused on spontaneous speech, it gives hearing-impaired people the option to transcribe conversations with spontaneous speech so they’re able to read the transcription in real-time and can use this information to communicate, respond, or be informed.

The app also offers the option of uploading files - audio recordings can be uploaded for transcription as well.

How can I use voice memos on the Speaker app?

For recorded voice memos simply upload the file to Speaker app, choose the correct language and have the memo transcribed. Once transcribed, the memo can be downloaded in various formats.

Speaker by Feelingstream accepts files in the following formats: .mp3, .wav, .aac, .ogg, .m4a.

Start transcribing today, speed up your workflow!
Listen and be present. You can read it over later.
Sign up!

Speaker for business?

Read more about Speaker in business and look at some examples on our business page.
Email us for more information at

This website uses cookies to ensure you get the best experience on our website.

Click here to accept.