Why Should I Use an API Key?
Simple: it's completely free for you. When you add your own Google Cloud API key in ShareSpeak, you're using Google's free tier directly—we don't charge you anything for transcription. You get generous free usage from Google, and after that, their rates are incredibly affordable.
Why Gemini 2.5 Flash Native Audio?
We chose Gemini 2.5 Flash for a reason. It scored 92% on the Big Bench Audio dataset, setting a new record for speech-to-speech reasoning. But here's what makes it special: Gemini 2.5 reasons directly over spoken words without converting them to text first. That means fewer steps where things can go wrong and more natural audio processing.
The accuracy of audio-to-text transcription has been significantly enhanced, and it provides seamless multilingual support—it can effortlessly switch between languages without any pre-configuration. Perfect for when you're recording in multiple languages or have speakers with different accents.
The best part? It's incredibly fast. The non-thinking version responds in just 0.63 seconds—faster than anything else out there. Plus, backed by decades of Google research in speech recognition and natural language understanding, Gemini delivers highly accurate transcriptions that capture the nuances of conversations.
Source: Artificial Analysis benchmarks, 2025
We're Building ShareSpeak With You
We're still in beta, which means we're young and hungry to make this better. Your feedback shapes what we build next.
Coming this quarter:
- GPT processing mode for enhanced transcription
- Supporting local models like Whisper/Ollama for offline and native use
- Improved design + glass morphism support
We believe in building together. That's why we're transparent about our tech choices and our roadmap. Gemini 2.5 Flash's native audio processing gives us cutting-edge accuracy today, while we work on bringing you more options tomorrow.
Have Questions or Feedback?
Share your ideas, report issues, or let us know what features you'd like to see next.