> ## Documentation Index
> Fetch the complete documentation index at: https://developers.namuai-lab.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Voices and languages

> Listen to each voice, then pick the one that fits the people who will hear it.

`/v1/speech` speaks with one of these voices. Each recording below was made through the API. Press play to hear it: nothing downloads until you do.

| Voice | `voice` | Languages | Notes |
| - | - | - | - |
| Nadia | `nadia` | Hausa | The default. Female, warm and patient. |
| Nadia | `warm` | Hausa | Another name for `nadia`. |
| Mouhamad | `mouhamad` | Zarma, Hausa | Male. Speaks Zarma unless you send `"language": "ha"`. |
| French | `fr` | French | The French reference voice. |

Every voice is used with its speaker's consent. The API does not offer voice cloning, and a voice whose consent could not be confirmed was withdrawn: a request that names it gets `400 unknown_voice`, never another voice in its place.

## Choosing the language

A voice speaks its first language unless you say otherwise. To make Mouhamad speak Hausa:

```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
{ "text": "Sannu! Yaya kuke?", "voice": "mouhamad", "language": "ha" }
```

Asking a voice for a language it does not speak returns `400 unsupported_language`, with the languages it does speak in the message.

## Languages

| Language | Code | Where people speak it | Speech to text | Text to speech | Translation |
| - | - | - | :-: | :-: | :-: |
| Hausa | `ha` | Niger, Nigeria and across West Africa | ✓ | ✓ | ✓ (with French) |
| Zarma | `dje` | Western Niger, along the river | ✓ | ✓ | |
| French | `fr` | Spoken across Niger and West Africa | ✓ | ✓ | ✓ (with Hausa) |

> [!NOTE]
>
> Fulfulde and Tamasheq are part of the Lab's research, not of the API yet. We add a language to the API when we can measure that it works.

## Get the list in code

```bash theme={"theme":{"light":"github-light","dark":"github-dark"}}
curl https://api.namuai-lab.com/v1/voices
```

```json theme={"theme":{"light":"github-light","dark":"github-dark"}}
{
  "data": [
    { "id": "nadia", "languages": ["ha"], "language": "ha", "description": "Warm and patient (female)" },
    { "id": "warm", "languages": ["ha"], "language": "ha", "description": "Alias of nadia" },
    { "id": "fr", "languages": ["fr"], "language": "fr", "description": "French reference voice" },
    { "id": "mouhamad", "languages": ["dje", "ha"], "language": "dje", "description": "Male; Zarma and Hausa" }
  ]
}
```

No key is needed. Read it when your app starts if you show a voice picker, so a new voice appears without an update.


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