RodiumAi docs
Core concepts

Text to speech

Send JSON with model and input; receive audio bytes (e.g. mp3). Billed in RODI.

POSThttps://api.rodiumai.io/v1/audio/speech

Call POST /v1/audio/speech with a TTS model id. The OpenAI SDK audio.speech.create helper works when base_url points at RodiumAi.

Examples

Request parameters

ParameterTypeRequiredDescription
modelstringRequiredTTS model id (e.g. openai/tts-1, google/gemini-2.5-flash-preview-tts).
inputstringRequiredText to synthesize into speech.
voicestringOptionalVoice id when supported (e.g. "alloy", "nova").
response_formatstringOptionalAudio format when supported (e.g. "mp3", "opus", "wav").
speednumberOptionalPlayback speed multiplier when supported (typically 0.25–4.0).
instructionsstringOptionalOptional speaking style / delivery instructions when the model supports them.

API reference: speech