QuietForge API
Drop-in for the OpenAI SDKs

OpenAI‑compatible speech & embeddings on Tenstorrent

OpenAI-compatible speech-to-text (Whisper large-v3) and text embeddings (BGE-M3), billed per use from your QuietForge wallet. Create a key on your account page.

Pay per useFailed requests are freeWebhooks for long jobs
quickstart.py
from openai import OpenAI

client = OpenAI(base_url="https://quietforge-api.badgerbite.io/v1",
                api_key="qfk_...")

# Whisper large-v3 speech-to-text
with open("meeting.mp3", "rb") as f:
    text = client.audio.transcriptions.create(
        model="whisper-1", file=f)

# BGE-M3, 1024-dimensional vectors
vecs = client.embeddings.create(
    model="bge-m3", input=["hello", "world"])
Speech

Whisper large-v3

Transcribe or translate audio into English. JSON, text, SRT, VTT or verbose JSON.

Embeddings

BGE-M3

Normalised 1024-dimensional vectors, up to 256 inputs per request.

Billing

Prepaid, per use

We reserve an estimate, then charge what was actually used. No subscription.

Endpoints

POSThttps://quietforge-api.badgerbite.io/v1/audio/transcriptions

Multipart file, model (whisper-large-v3 or whisper-1), optional language, prompt, response_format (json, text, srt, vtt, verbose_json)

POSThttps://quietforge-api.badgerbite.io/v1/audio/translations

The same, translating into English

On both audio endpoints, language is the source language of the audio (an ISO-639-1 code such as fr). Without it the audio is treated as English, because automatic language detection is not available yet: send language for any non-English audio, including audio you want translated.

POSThttps://quietforge-api.badgerbite.io/v1/embeddings

JSON {"model": "bge-m3", "input": ["..."]}, 1024-dimensional normalised vectors

GEThttps://quietforge-api.badgerbite.io/v1/models
GEThttps://quietforge-api.badgerbite.io/v1/jobs/{id}

Prices

ModelJobPrice
bge-m3embedding $0.00002 per started 1k tokens
whisper-large-v3transcription $0.003 per started audio minute
whisper-large-v3translation $0.003 per started audio minute

We reserve an estimate when a request starts and charge what was actually used. Failed requests are free.

Examples

cURL · transcription
curl https://quietforge-api.badgerbite.io/v1/audio/transcriptions -H "Authorization: Bearer $QF_KEY" \
  -F file=@meeting.mp3 -F model=whisper-1 -F response_format=srt
Python · embeddings
from openai import OpenAI
client = OpenAI(base_url="https://quietforge-api.badgerbite.io/v1", api_key="qfk_...")
client.embeddings.create(model="bge-m3", input=["hello", "world"])

Long audio, async and webhooks

Requests wait up to 60 s. A synchronous call that runs out of time does not fail: it returns 202 with a job object ({"id", "object", "status", "poll"}) instead of the transcript, and the job keeps running. The OpenAI SDKs don't expect that response, so for long audio send sync=false (with the SDK, extra_body={"sync": "false"}) and poll /v1/jobs/{id}, or add a callback_url. We POST the job to your URL with the header X-QF-Signature: t=…,v1=…, an HMAC-SHA256 of "{t}.{body}" using your key's webhook secret. Check the signature and reject stale timestamps:

Python · verify a webhook
import hmac, hashlib, time
t, v1 = (p.split("=", 1)[1] for p in header.split(","))
ok = hmac.compare_digest(v1, hmac.new(secret.encode(), f"{t}.".encode() + body, hashlib.sha256).hexdigest())
if not ok or abs(time.time() - int(t)) > 300:
    reject()

Errors about a job that already exists carry X-QF-Job-Id and x-should-retry: false, so the SDK doesn't retry and start a second job: check /v1/jobs/{id} first.

Webhooks are delivered at least once. If a delivery times out or fails, we retry it, so treat a repeated payload with the same job id and state as a duplicate.

Limits

Audio up to 25 MiB and 2 hours; a prompt of up to 224 tokens. Up to 256 embedding inputs per request, each at most 8192 tokens (longer inputs are rejected, not truncated).