# Namu API

> Speech recognition, speech synthesis, translation and a voice agent for Hausa, Zarma and French.

- [Namu API](https://developers.namuai-lab.com/index.md): Speech recognition, speech synthesis, translation and a voice agent for Hausa, Zarma and French, through one key.
- [Quickstart](https://developers.namuai-lab.com/quickstart.md): Create a key, make your first request, and hear a sentence spoken in Hausa.
- [Pricing and limits](https://developers.namuai-lab.com/pricing-and-limits.md): Free during the beta: 30 minutes of audio a month for every account. Here is how it is counted, and the limits on each request.
- [SDKs](https://developers.namuai-lab.com/sdks/overview.md): Use the Namu API from Python, JavaScript, Android, iOS or any language that speaks HTTP.
- [Python](https://developers.namuai-lab.com/sdks/python.md): The official Python library for the Namu API: speech, transcription, translation and the voice agent.
- [JavaScript and TypeScript](https://developers.namuai-lab.com/sdks/javascript.md): The official JavaScript and TypeScript library for the Namu API, with no dependencies, for Node, Deno, Bun and Cloudflare Workers.
- [Any language (HTTP)](https://developers.namuai-lab.com/sdks/http.md): Call the API with curl or any HTTP library, or generate a client from the OpenAPI file.
- [Android (Kotlin)](https://developers.namuai-lab.com/sdks/android.md): Record a voice note, have it transcribed, and play speech back, with the key safe on your server.
- [iOS (Swift)](https://developers.namuai-lab.com/sdks/ios.md): Record, transcribe and speak from an iPhone app, with the key safe on your server.
- [Changelog](https://developers.namuai-lab.com/resources/changelog.md): What changed in the Namu API, newest first.
- [Help and support](https://developers.namuai-lab.com/resources/support.md): Where to ask, what to include, and how to check that the API is up.
- [Responsible use](https://developers.namuai-lab.com/resources/responsible-use.md): Voices carry trust. How to use the API so that the people who hear and speak to your app can keep trusting it.
- [Glossary](https://developers.namuai-lab.com/resources/glossary.md): The words these docs use, in one place.
- [Models](https://developers.namuai-lab.com/models.md): Four models, one per task. What each one does, its languages, and how ready it is.
- [Voices and languages](https://developers.namuai-lab.com/voices-and-languages.md): Listen to each voice, then pick the one that fits the people who will hear it.
- [Text to speech](https://developers.namuai-lab.com/capabilities/text-to-speech.md): Turn text into natural speech in Hausa, Zarma or French, with a voice your listeners will trust.
- [Audio formats](https://developers.namuai-lab.com/guides/audio-formats.md): What the API accepts, what it returns, and how to keep files small.
- [Read messages aloud in Hausa](https://developers.namuai-lab.com/tutorials/read-aloud-in-hausa.md): Turn a list of messages into small audio files, generated once and reused.
- [Voice reminders for a health centre](https://developers.namuai-lab.com/tutorials/voice-messages-for-a-clinic.md): Spoken vaccination reminders built from parts, so the same sentence is never paid for twice.
- [Speech to text](https://developers.namuai-lab.com/capabilities/speech-to-text.md): Turn recordings and voice notes into text, in Hausa, Zarma or French.
- [Transcribe a WhatsApp voice note](https://developers.namuai-lab.com/tutorials/transcribe-a-voice-note.md): From a voice note on your phone to text on your screen, without converting anything.
- [Translation](https://developers.namuai-lab.com/capabilities/translation.md): Hausa to French and French to Hausa, from text or straight from speech, with the translation spoken if you want it.
- [Build a Hausa ⇄ French interpreter](https://developers.namuai-lab.com/tutorials/hausa-french-interpreter.md): A web page where one person speaks Hausa, the other hears French, and back again.
- [Voice agent](https://developers.namuai-lab.com/capabilities/voice-agent.md): A spoken conversation in Hausa: send what someone said, get back the reply as text and as speech.
- [Talk to the voice agent](https://developers.namuai-lab.com/tutorials/talk-to-the-voice-agent.md): A spoken conversation in Hausa from your terminal: record, send, listen, repeat.
- [Production checklist](https://developers.namuai-lab.com/guides/production-checklist.md): Before real people depend on your app, go through this list.
- [API keys](https://developers.namuai-lab.com/guides/api-keys.md): Create keys, give each one only what it needs, and keep them off phones and web pages.
- [Errors](https://developers.namuai-lab.com/guides/errors.md): Every error has the same shape, a stable code to branch on, and a request id to send us.
- [Usage and rate limits](https://developers.namuai-lab.com/guides/usage-and-rate-limits.md): How requests are counted, how to check where you stand, and how to stay inside the limits.
- [Building for weak networks](https://developers.namuai-lab.com/guides/weak-networks.md): Most people who will hear your app are on phones, on mobile data that is slow, costly and drops. Design for that from the first line.
- [Your first call in five minutes](https://developers.namuai-lab.com/tutorials/first-call.md): Create a key, send one request, and hear your app speak Hausa.
- [Watch your usage](https://developers.namuai-lab.com/tutorials/watch-your-usage.md): A daily check that warns you before the month's allowance runs out.
- [API reference](https://developers.namuai-lab.com/api-reference/introduction.md): Every endpoint, field and response of the Namu API. Try each one from this page with your own key.
- [Authentication](https://developers.namuai-lab.com/api-reference/authentication.md): Send your secret key as a bearer token.
- [Errors](https://developers.namuai-lab.com/api-reference/errors.md): One error shape for every endpoint.
- [Create speech](https://developers.namuai-lab.com/api-reference/speech/create-speech.md): Turns text into spoken audio in Hausa, Zarma or French. Counts the length of the audio returned against your monthly allowance. Needs the `speech` scope.
- [Create transcription](https://developers.namuai-lab.com/api-reference/transcription/create-transcription.md): Writes down what was said in a recording. Send the audio as a multipart field named `file`, or as the raw request body with `language` in the query string. The container is recognised from the file itself: WAV, MP3, M4A/AAC, OGG/Opus (WhatsApp voice notes), WebM, FLAC. Up to 25 MB and 300 seconds. C…
- [Create translation](https://developers.namuai-lab.com/api-reference/translation/create-translation.md): Translates between Hausa and French, in both directions. Send JSON to translate text, or audio (multipart `file`, or the raw body) to translate speech. Add `include_audio` to also get the translation spoken. Text counts its characters divided by 15 as seconds; speech counts the audio sent. Needs the…
- [Converse](https://developers.namuai-lab.com/api-reference/voice-agent/converse.md): One turn of a spoken conversation in Hausa: send what the person said, get back what was heard, the reply as text and the reply spoken. A research preview. New keys do not include the `converse` scope: tick it when you create the key. Counts the audio sent plus the reply.
- [List models](https://developers.namuai-lab.com/api-reference/models-and-voices/list-models.md): The four models, the endpoint each serves and its languages. No key needed.
- [List voices](https://developers.namuai-lab.com/api-reference/models-and-voices/list-voices.md): The voices `/v1/speech` speaks with, and their languages. No key needed.
- [Get usage](https://developers.namuai-lab.com/api-reference/account/get-usage.md): Audio seconds counted this calendar month (UTC) and your allowance. Needs a key, any scope. May lag by up to 30 seconds.
- [Health](https://developers.namuai-lab.com/api-reference/account/health.md): Whether the API is answering. No key needed.

## OpenAPI Specs

- [openapi](/api-reference/openapi.yaml)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.