Quickstart

The Namu API is a plain HTTPS API: every request is a POST or a GET to https://api.namuai-lab.com/v1/... with your key in the Authorization header. Anything that can send HTTP can use it.

Create an API key

Sign in to the Namu console and open API keys. Create a key, give it a name you will recognise, and copy it. It starts with namu_sk_ and is shown once.

Your key is a password. Keep it on your server: never put it in a mobile app, a web page or a public repository. Anyone holding it can spend your allowance.

Save the key as an environment variable

Your code reads the key from the environment, so it never sits in a file you might share.

export NAMU_API_KEY="namu_sk_..."

setx NAMU_API_KEY "namu_sk_..."

On Windows, open a new terminal afterwards so it sees the variable.

Make your first request

Ask Nadia to say “Sannu da zuwa! Muna farin cikin jin muryarku.” (Welcome! We are glad to hear your voice.)

curl https://api.namuai-lab.com/v1/speech \
  -H "Authorization: Bearer $NAMU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"text": "Sannu da zuwa! Muna farin cikin jin muryarku.", "voice": "nadia"}' \
  -o welcome.wav

import os
import requests

response = requests.post(
    "https://api.namuai-lab.com/v1/speech",
    headers={"Authorization": f"Bearer {os.environ['NAMU_API_KEY']}"},
    json={"text": "Sannu da zuwa! Muna farin cikin jin muryarku.", "voice": "nadia"},
    timeout=120,
)
response.raise_for_status()

with open("welcome.wav", "wb") as f:
    f.write(response.content)
print("Saved", response.headers["X-Audio-Seconds"], "seconds of audio")

import { writeFile } from "node:fs/promises";

const response = await fetch("https://api.namuai-lab.com/v1/speech", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.NAMU_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({ text: "Sannu da zuwa! Muna farin cikin jin muryarku.", voice: "nadia" }),
});
if (!response.ok) throw new Error((await response.json()).error.message);

await writeFile("welcome.wav", Buffer.from(await response.arrayBuffer()));
console.log("Saved", response.headers.get("X-Audio-Seconds"), "seconds of audio");

Play it

Open welcome.wav. That is your app speaking Hausa. The first request after a quiet spell can take a little longer while the model wakes up; the next ones are faster.

Now let it listen

Send the file you just made back to the API and read what it heard:

curl https://api.namuai-lab.com/v1/transcribe \
  -H "Authorization: Bearer $NAMU_API_KEY" \
  -F file=@welcome.wav \
  -F language=ha

with open("welcome.wav", "rb") as audio:
    response = requests.post(
        "https://api.namuai-lab.com/v1/transcribe",
        headers={"Authorization": f"Bearer {os.environ['NAMU_API_KEY']}"},
        files={"file": audio},
        data={"language": "ha"},
        timeout=120,
    )
print(response.json()["text"])

import { readFile } from "node:fs/promises";

const form = new FormData();
form.append("file", new Blob([await readFile("welcome.wav")]), "welcome.wav");
form.append("language", "ha");

const heard = await fetch("https://api.namuai-lab.com/v1/transcribe", {
  method: "POST",
  headers: { Authorization: `Bearer ${process.env.NAMU_API_KEY}` },
  body: form,
}).then((r) => r.json());
console.log(heard.text);

Response

{
  "model": "speech-recognition",
  "text": "sannu da zuwa muna farin cikin jin muryarku",
  "language": "ha",
  "audio_seconds": 3.1
}

Transcripts are written in lower case, without punctuation. Add your own if your screen needs it.

Next steps

Choose a voice

Nadia in Hausa, Mouhamad in Zarma and Hausa, and the French voice.

Translate

Hausa to French and back, from text or from speech.

Use an SDK

A small Python or JavaScript client you can paste into your project.

Watch your usage

How each request is counted against your 30 free minutes.

Get started

SDKs and tools

Mobile apps

Resources

Now let it listen

Next steps

Choose a voice

Translate

Use an SDK

Watch your usage

​Now let it listen

​Next steps

Choose a voice

Translate

Use an SDK

Watch your usage

Now let it listen

Next steps