gemini-audio

Here are 3 public repositories matching this topic...

MHJoy99 / joyvoice

Instant Windows voice typing: hold F8, speak English, Bangla or Banglish, get polished English in ~1 s. ElevenLabs realtime + Gemini Transcribe Live, GPU-animated glass widget, offline mode.

windows open-source accessibility speech-recognition speech-to-text gemini-api voice-dictation speech-translation audio-transcription bangla-to-english voice-typing pyside6 floating-widget bangla-asr elevenlabs windows-dictation gemini-audio banglish-translation realtime-dictation

Updated Oct 15, 2026
Python

AbdulRehmanRattu / multimodal-voice-studio

Star

Professional AI voiceover synthesis pipeline leveraging Gemini 2.5 Native Audio and OpenAI TTS with expressive script-directed emotional modulation.

python text-to-speech audio-processing generative-ai openai-tts multimodal-ai gemini-audio voiceover-ai

Updated Sep 2, 2026
Python

mokenyu / craptcha-tts

Star

Telegram channel scraper and TTS reader built with Telethon, FastAPI, and Gemini Native Audio streaming for real-time 24kHz PCM voice playback.

python text-to-speech telethon pcm-streaming telegram-scraper fastapi tts-reader gemini-audio

Updated Jul 30, 2026
Python

Add this topic to your repo

To associate your repository with the gemini-audio topic, visit your repo's landing page and select "manage topics."

Learn more