OpenAI API drop-in

import osfrom openai import OpenAIclient = OpenAI(    base_url="https://api.ttscacherouter.dev/openai/v1",    api_key=os.environ["TTS_CACHE_ROUTER_API_KEY"],)with client.audio.speech.with_streaming_response.create(    model="gpt-4o-mini-tts",    voice="ash",    input="Your order has shipped. It arrives on Friday.",    instructions="Speak in a warm, friendly tone.",) as response:    response.stream_to_file("speech.mp3")

audio.speech.create works through the router with every model, voice, format and setting, streamed or not. Requests, responses, status codes and error bodies are OpenAI’s own; your body is forwarded as you sent it, with the OpenAI key stored under Provider keys. For a LiveKit agent, see OpenAI with LiveKit.

This is OpenAI’s API, with OpenAI’s model names. The router’s own /v1/audio/speech takes the same request with openai/gpt-4o-mini-tts as the model, and serves every provider.

• POST /openai/v1/audio/speech: the audio in the requested response_format, or with stream_format: "sse" OpenAI’s speech.audio.delta events (tts-1 and tts-1-hd answer that with the audio, as OpenAI does).

Any other path under /openai answers 404.

curl -N https://api.ttscacherouter.dev/openai/v1/audio/speech \  -H "Authorization: Bearer $TTS_CACHE_ROUTER_API_KEY" \  -H "Content-Type: application/json" \  -d '{"model": "tts-1", "voice": "alloy", "input": "Your order has shipped.", "response_format": "pcm"}' \  --output speech.pcm

curl -N https://api.ttscacherouter.dev/openai/v1/audio/speech \  -H "Authorization: Bearer $TTS_CACHE_ROUTER_API_KEY" \  -H "Content-Type: application/json" \  -d '{"model": "gpt-4o-mini-tts", "voice": "ash", "input": "Your order has shipped.",       "response_format": "pcm", "stream_format": "sse"}'

• Each request as a whole: the same body again replays the same audio, in every format.
• With stream_format: "sse", a reply from the cache sends the same speech.audio.delta events, then speech.audio.done with zero usage (OpenAI spent no tokens on it), then [DONE].
• A reply from the cache carries only Content-Type: no OpenAI request produced it, so there is no x-request-id.
• gpt-4o-mini-tts is an alias OpenAI can move to a newer snapshot; audio already cached under it keeps the voice it was made with. To pin the voice, name a snapshot such as gpt-4o-mini-tts-2025-12-15.

A wrong or missing router key gets OpenAI’s own refusal, HTTP 401. So does an org with no OpenAI key stored, with a message that links to the dashboard. Errors from OpenAI, such as a voice the model doesn’t have, reach you as OpenAI sent them.

HTTP/1.1 401 Unauthorized{"error": {"message": "Incorrect API key provided.", "type": "invalid_request_error",           "param": null, "code": "invalid_api_key"}}