GLM ASR 2512 API

Quickstart

Speech-to-text uses /v1/run. Pass `inputs.audio` as a public URL to the audio file (wav/mp3/m4a/ogg/flac/webm) — stereo is auto-downmixed to mono. The response returns the transcribed `text`. Token-billed on audio (input) + text (output) tokens.

bashcurl --max-time 120 https://api.skillboss.co/v1/run \
  -H "Authorization: Bearer $SKILLBOSS_WHOLESALE_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm/glm-asr-2512",
    "inputs": {
      "audio": "https://interactive-examples.mdn.mozilla.net/media/examples/t-rex-roar.mp3"
    }
  }'

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": "glm/glm-asr-2512",
        "inputs": {
            "audio": "https://interactive-examples.mdn.mozilla.net/media/examples/t-rex-roar.mp3",
        },
    },
    timeout=120,
)
data = resp.json()
print(data["text"])  # transcribed text

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: "glm/glm-asr-2512",
    inputs: {
      audio: "https://interactive-examples.mdn.mozilla.net/media/examples/t-rex-roar.mp3",
    },
  }),
});
const data = await resp.json();
console.log(data.text);  // transcribed text

Parameters

Pass the model identifier as a top-level model field, and the audio source under an inputs object. Set inputs.audio to a public URL of the audio file; the response returns the transcribed text.

Endpoint

Errors

The API uses standard HTTP status codes:

Pricing