API Documentation

9jaLingo API Reference

Official Python and Node.js SDKs for African languages. Generate natural, expressive speech in Hausa, Igbo, Yoruba, and Pidgin English with 240+ speaker voices and real-time streaming.

pip install naijalingonpm install naijalingo

Text to Speech

Natural speech in 4 African languages with 240+ voices.

Real-time Streaming

Stream audio chunks as they are generated for long texts.

Voice Cloning

Clone any voice from a short reference audio sample.

Multi-language

Hausa, Igbo, Yoruba, and Nigerian Pidgin.

1Installation

Install the Python or Node.js SDK, or call the REST API directly with cURL.

terminal

# 1) Install the official SDK (Python 3.11+)pip install naijalingo # 2) Copy your real key from https://9jalingo.org/dashboard# 3) Paste it below — replace YOUR_API_KEY (do not leave this as-is)export NAIJALINGO_API_KEY="YOUR_API_KEY"

Replace YOUR_API_KEY with your real key from 9jalingo.org/dashboard. Leaving the placeholder returns {"detail":"Invalid API Key"} and saves a broken audio file. Later examples assume NAIJALINGO_API_KEY is already set in your shell.

2Quick start

Get speech output in under 60 seconds.

quickstart

from naijalingo import NaijaLingo # Uses NAIJALINGO_API_KEY from step 1 (do not hard-code nl-... placeholders)client = NaijaLingo() # voice/speaker = speaker ID · lang/language = language codeaudio = client.tts.generate(    "Bawo ni, I dey greet you!",    voice="adeola_yo",    lang="yo",)audio.save("greeting.wav") audio = client.tts.generate("Sannu da zuwa!", speaker="aisha_ha", language="ha")audio.save("output.wav")

Text-to-Speech

Generate speech with a speaker ID in voice / speaker(e.g. ada_pcm) and an optional language in lang / language(ha / ig / yo / pcm). Returns WAV by default. Use response_format to export to MP3, FLAC, AAC, OGG, ALAC, or PCM.

POST/v1/audio/speech

tts-generate

from naijalingo import NaijaLingo # Uses NAIJALINGO_API_KEY from step 1client = NaijaLingo() # voice/speaker = speaker ID · lang/language = language codeaudio = client.tts.generate("How you dey?", voice="ada_pcm", lang="pcm")audio.save("output.wav") # speaker= / language= aliasesaudio = client.tts.generate(    "Nnoo, kedu ka i mere?",    speaker="adaeze_ig",    language="ig",)audio.save("adaeze_greeting.wav") # Export to MP3, FLAC, AAC, OGG, ALAC, or PCMaudio = client.tts.generate(    "Make we test compressed audio.",    voice="ada_pcm",    lang="pcm",    response_format="mp3",)audio.save("output.mp3") # Fine-tune generation parametersaudio = client.tts.generate(    "Na so life be sometimes.",    voice="ada_pcm",    lang="pcm",    temperature=0.8,    top_p=0.9,    repetition_penalty=1.2,)

Parameter	Type	Required	Description
`input`	string	required	The text to synthesize. (SDK: first positional arg to generate/stream.)
`model`	string?	optional	Model ID, e.g. "9jalingo-tts-1". Defaults to the active model if omitted.
`voice`	string?	optional	Speaker ID (e.g. ada_pcm, adaeze_ig). Alias: speaker. Not a language code.
`speaker`	string?	optional	Alias of voice — speaker ID. Takes precedence over voice when both are set.
`lang`	string?	optional	Language code: ha · ig · yo · pcm. Alias: language. Auto-inferred from speaker suffix if omitted.
`language`	string?	optional	Alias of lang.
`response_format`	string?	optional	wav (default) · pcm · mp3 · flac · aac · alac · ogg
`temperature`	float?	optional	Sampling temperature (0.0 – 1.5). Default: 0.95.
`top_p`	float?	optional	Nucleus sampling (0.0 – 1.0). Default: 0.95.
`repetition_penalty`	float?	optional	Repetition penalty (1.0 – 1.5). Default: 1.1.