Together AI Audio TTS/STT Skill for Claude Code

What is This Skill?

This skill teaches AI coding agents how to use Together AI's audio API for text-to-speech and speech-to-text. It covers REST TTS, streaming TTS via WebSocket, and speech-to-text transcription — with correct SDK patterns for each mode.

Answer-Ready: Together AI Audio Skill for coding agents. Covers TTS (REST + WebSocket streaming), STT transcription, and realtime voice. Correct SDK patterns and model IDs. Part of official 12-skill collection.

Best for: Developers building voice-enabled AI applications. Works with: Claude Code, Cursor, Codex CLI.

What the Agent Learns

Text-to-Speech (REST)

from together import Together

client = Together()
response = client.audio.speech.create(
    model="together-ai/tts-model",
    input="Hello, welcome to the demo!",
    voice="alloy",
)
response.stream_to_file("output.mp3")

Streaming TTS (WebSocket)

# Low-latency streaming for realtime applications
import websocket
# WebSocket connection for chunked audio streaming

Speech-to-Text

with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="together-ai/whisper",
        file=f,
    )
print(transcript.text)

FAQ

Q: What voices are available? A: Multiple voices supported. Check Together AI docs for current voice list.