Speaches

Speech AI (STT/TTS) playground.

Overview

Speaches provides speech-to-text and text-to-speech capabilities using:

• Whisper for transcription
• Various TTS models

URL

• UI: https://speaches.meetrhea.com
• API: https://speaches.meetrhea.com/v1

OpenAI-Compatible API

# Text-to-Speech
response = client.audio.speech.create(
    model="tts-1",
    voice="alloy",
    input="Hello world"
)

# Speech-to-Text
with open("audio.mp3", "rb") as f:
    transcript = client.audio.transcriptions.create(
        model="whisper-1",
        file=f
    )