Search Results for "mega-voice"

sag is a command-line text-to-speech utility inspired by the macOS say command but powered by modern ElevenLabs voice synthesis technology. The project allows users to stream synthesized speech directly to speakers, save audio files, or list and manage available voices through a lightweight terminal interface. Designed for speed and convenience, sag supports voice selection, playback rate adjustments, output format inference, and configurable API endpoints for flexible deployment. ...

...It integrates several stages of the pipeline: video acquisition (either from local files or remote via download tools), speech recognition (ASR), subtitle segmentation and alignment, machine translation (with context-aware translation to preserve semantics), and voice cloning + text-to-speech (TTS) to produce dubbed audio tracks. KrillinAI supports both landscape and portrait videos, which makes it suitable for a wide range of platforms — from YouTube to TikTok or other vertical-video sites — and ensures correct formatting and layout for the final video. The tool offers “one-click” workflows and desktop versions, lowering the barrier for users who may not be familiar with video editing or audio processing pipelines.

DiscordGo is a Go package that provides low level bindings to the Discord chat client API. DiscordGo has nearly complete support for all of the Discord API endpoints, websocket interface, and voice interface. If you would like to help the DiscordGo package please use this link to add the official DiscordGo test bot dgo to your server. This provides indispensable help to this project. Construct a new Discord client which can be used to access the variety of Discord API functions and to set callback functions for Discord events. ...

Feishu × (GPT-3.5 + DALL·E + Whisper) = flying-like work experience. Voice dialogue, role-playing, multi-topic discussion, picture creation, table analysis, document export. Golang language, it goes without saying! Master the gin framework proficiently, developing the backend is as natural as breathing! Familiar with the SDKs of DingTalk, Feishu, Qiwei and other platforms, and be able to develop and integrate a series of amazing functions!

...Its goal is to provide a free and open-source alternative to big services like DialogFlow. You can chat with her by speaking (STT) or writing, she replies with a text message but you can enable her voice (TTS). Olivia can listen to you by saying “Hey Olivia” or clicking on the central button. She speaks to reply to you unless you've disabled her voice. Olivia respects your privacy. All the data used by Olivia is saved in your client. Olivia is organized in modules to facilitate the addition of new capabilities. These modules can be written in Go to execute multiple tasks. ...