Generate audio from text and transcribe audio using Together AI APIs.
npx skills add https://github.com/zainhas/togetherai-skills --skill together-audio
Please help me install this Agent Skill. Skill: together-audio Source: https://github.com/zainhas/togetherai-skills/tree/main/skills/together-audio Command: npx skills add https://github.com/zainhas/togetherai-skills --skill together-audio
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.
Create a short example that converts text to speech using a chosen model and saves the output to a file.
High-intent search queries and answers about installing and using this skill.
You can convert text to speech and transcribe audio using the Together AI API by implementing REST, streaming, and WebSocket endpoints. This skill provides runnable scripts and reference docs to handle both TTS and STT workflows end-to-end.
Yes, real-time audio transcription and translation are supported using WebSocket connections. You can leverage Whisper, Voxtral, Parakeet, and Deepgram models to diarize and transcribe streaming audio inputs directly.
The best way to build a podcast workflow is combining TTS for generating intros and outross with STT for creating captions. This skill unifies these voice-enabled applications using Together AI's Python and TypeScript SDKs.
Yes, you need the Together Python SDK to generate speech from text across multiple voices. The skill relies on both the Python and TypeScript SDKs to interact with REST and WebSocket APIs for audio generation.
Yes, Together AI supports speaker diarization and audio translation within speech-to-text workflows. You can transcribe and translate audio using Whisper, Voxtral, Parakeet, and Deepgram endpoints provided in the skill.
AlvaGonzStream live audio, video, and text bidirectionally with Gemini Live API over WebSockets.
pavan53732Generate podcast scripts and WAV audio from text or web search results.
storyclaw-officialGenerate spoken audio from text using the ElevenLabs TTS engine.
lemonlqfTranscribe and translate audio and video files into text or subtitles using the Whisper CLI.
