MiniMax Speech 2.8 HD API

Quickstart

Audio generation uses /v1/run. TTS models accept `inputs.text` + optional `inputs.voice_id` and are billed per input character. Music generation accepts `inputs.lyrics` + optional style `inputs.prompt` and is billed per successful generation. Response includes a signed URL to the generated MP3 (fetch within ~24h before the link expires).

bashcurl https://api.skillboss.co/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_WHOLESALE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "minimax_voice/speech-2.8-hd",
    "inputs": {
      "text": "Hello, this is a SkillBoss text-to-speech demo.",
      "voice_id": "female-shaonv"
    }
  }'

Your first 200 response is the fastest way to confirm setup. From there, swap in your real prompt and tune the model-specific parameters listed below.

Authentication

Every request must include your wholesale key. The header name depends on the endpoint — match the SDK you're using:

bashAuthorization: Bearer $SKILLBOSS_WHOLESALE_KEY

Treat the wholesale key like a password — never commit it to source control or ship it in client-side bundles. Rotate from the wholesale dashboard if exposed. Standard (non-wholesale) console keys are rejected at the gateway with 401.

Code examples

pythonimport os, requests

resp = requests.post(
    "https://api.skillboss.co/v1/run",
    headers={"Authorization": f"Bearer {os.environ['SKILLBOSS_WHOLESALE_KEY']}"},
    json={
        "model": "minimax_voice/speech-2.8-hd",
        "inputs": {
            "text": "Hello, this is a SkillBoss text-to-speech demo.",
            "voice_id": "female-shaonv",
        },
    },
    timeout=60,
)
data = resp.json()
print(data["outputs"][0]["url"])  # signed URL to the generated audio

typescriptconst resp = await fetch("https://api.skillboss.co/v1/run", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.SKILLBOSS_WHOLESALE_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "minimax_voice/speech-2.8-hd",
    inputs: {
      text: "Hello, this is a SkillBoss text-to-speech demo.",
      voice_id: "female-shaonv",
    },
  }),
});
const data = await resp.json();
console.log(data.outputs[0].url);  // signed URL to the generated audio

Parameters

Pass the model identifier as a top-level model field, and all generation parameters under an inputs object. TTS models use inputs.text + inputs.voice_id; music models use inputs.lyrics + inputs.prompt. See the model card on the wholesale dashboard for the full voice library and music style hints.

Endpoint

Errors

The API uses standard HTTP status codes:

Pricing