together-audio

Community

Turn text to speech and back with ease.

Authorzainhas
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Text-to-speech and speech-to-text workflows are often stitched together with ad-hoc tooling. This skill provides a unified set of instructions to generate audio from text and transcribe/translate audio using Together AI, enabling end-to-end voice-enabled applications.

Core Features & Use Cases

  • TTS: generate speech from text across multiple voices/models via REST, streaming, and WebSocket endpoints.
  • STT: transcribe, translate, and diarize audio using Whisper, Voxtral, Parakeet, and Deepgram endpoints with realtime WebSocket options.
  • Use Case: Build an automated podcast workflow that generates intros/outros and captions.

Quick Start

Create a short example that converts text to speech using a chosen model and saves the output to a file.

Dependency Matrix

Required Modules

websocketstogethertogether-ai

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: together-audio
Download link: https://github.com/zainhas/togetherai-skills/archive/main.zip#together-audio

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.