PindoDocs
Web AppWeb

VoiceAI API

Voice AI brings speech and language understanding to African languages. Convert speech to text, generate natural speech from text, and extract named entities, all over a simple REST API.

Base URL

All Voice AI endpoints are served under the /ai path on the Pindo API host.

https://api.pindo.io/ai

Public vs. authenticated access

Every model is reachable two ways. Append /public to call it without a token, ideal for prototyping, subject to per-IP rate limits. For production, drop the /public suffix and send a bearer token.

ModePathAuth
Public/ai/stt/rw/publicNone · rate-limited per IP
Authenticated/ai/stt/rwBearer token

Authenticated requests require an Authorization header. Get a token from the Messaging & CLI → Authentication guide, or read the source on pindo-ai-docs.

Authorization: Bearer YOUR_ACCESS_TOKEN

Supported languages

ModelLanguagesCodes
Speech-to-TextKinyarwanda, Kiswahili, Lugandarw · sw · lg
Text-to-SpeechKinyarwandarw
Named Entity RecognitionKinyarwanda, Englishrw · en