Namu API - Namu API

Developer quickstart

Make your first request in minutes: send a sentence in Hausa, Zarma or French and get it back as speech, or send a voice note and get its text.

Get started Create API key

Python

from namu import Namu

client = Namu()  # reads NAMU_API_KEY

audio = client.speech("Sannu da zuwa!", voice="nadia")
open("welcome.wav", "wb").write(audio)

import { writeFile } from "node:fs/promises";
import { Namu } from "namu-ai";

const namu = new Namu(); // reads NAMU_API_KEY

const audio = await namu.speech("Sannu da zuwa!", { voice: "nadia" });
await writeFile("welcome.wav", Buffer.from(audio));

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

Give Claude Code, Codex or Cursor the API as plain text: every page here has a Markdown copy, and llms.txt holds the whole API in one file.

Build paths

Speech APITurn text into speech, speech into text, and Hausa into French or back, with one key and plain HTTPS.Start with the quickstart SDKs for Python and JavaScriptpip install namu-ai or npm install namu-ai: typed responses, retries, and one error class per status.Start with the SDKs

Models

One model for each job, on its own endpoint, with the same limits and the same shape for every error.

speech-synthesisText to speechSpeaks Hausa, Zarma and French in three voices.Beta speech-recognitionSpeech to textWrites down Hausa, Zarma and French speech, voice notes included.Beta translationTranslationHausa to French and French to Hausa, from text or from speech.Beta voice-agentVoice agentOne spoken turn in Hausa: it listens, answers and speaks the answer.Research

Start building

Read messages aloudTurn reminders and lessons into speech in Hausa, Zarma or French Transcribe voice notesGet the text of a WhatsApp voice note or a phone recording Translate Hausa and FrenchBuild an interpreter that hears one language and answers in the other Talk with the voice agentSend a spoken question in Hausa and play the spoken reply Build for weak networksSmall audio, short waits and retries for phones on costly data Go to productionKeys, errors, limits and usage before real people use your app

Help and supportQuestions about your account, keys and usage ChangelogWhat changed in the API and the SDKs API referenceEvery endpoint, parameter and response Responsible useWhat the voices may and may not be used for