AI registry
AI Resources
African language models, speech & text datasets, and AI infrastructure.
13 results in Speech (ASR/TTS)
African-Whisper
An open-source framework (PyPI: africanwhisper) for fine-tuning OpenAI's Whisper on multilingual African-language audio datasets such as Common Voice and FLEURS, with optimized inference, diarization and deployment. Created by Kevin Kibe.
BibleTTS
BibleTTS is a large, high-fidelity open text-to-speech corpus with up to 80+ hours of studio-quality 48kHz single-speaker recordings per language across ten Sub-Saharan African languages (Akuapem Twi, Asante Twi, Chichewa, Ewe, Hausa, Kikuyu, Lingala, Luganda, Luo, Yoruba), built by Masakhane/Coqui.
EqualyzAI
EqualyzAI is a voice-first agentic AI company building speech recognition, text-to-speech and voice agents for African languages and dialects (Yoruba, Igbo, Hausa, Pidgin with code-switching), with products including VoiceMaker, VoiceAgent and VoiceBridge plus datasets/APIs. Operates from Lagos, Nigeria and Washington DC.
Intron Health
Intron Health is a Nigerian voice-AI company whose Sahara-v2 models deliver clinical/medical speech recognition (and TTS) optimized natively for African accents and dialects, trained on Africa's largest clinical speech database (millions of clips across 200+ accents). Serves healthcare, call-centre, legal and biometrics use cases via STT/TTS/voice-bot APIs.
Kallaama
A 125-hour transcribed speech dataset in Wolof, Pulaar and Sereer (the three most widely spoken languages of Senegal) focused on agriculture, built for ASR development. Led by Jokalante with Orange Innovation and Ecole Polytechnique de Thies, funded by Lacuna Fund.
Spitch
Spitch is a Lagos-based voice-AI company (founded Oct 2024) providing ASR (speech-to-text), TTS (text-to-speech) and translation APIs/SDKs for Nigerian languages (Yoruba, Igbo, Hausa, Nigerian-accented English, plus Amharic) so teams can add local-language voice to call centres, media and learning tools.
Sunbird AI SALT
SALT (Sunbird African Language Technology) is a multi-way parallel text-and-speech corpus of English plus Luganda, Acholi, Lugbara, Ateso, Runyankole and Swahili supporting ASR, TTS and translation, with companion Whisper and MMS models. Built with Makerere University AI Lab.
Vulavula
Vulavula is Lelapa AI's API platform for speech-to-text transcription and machine translation across South African and African languages (isiZulu, Sesotho, Sepedi, Setswana, isiXhosa, Afrikaans, English, Swahili, Hausa, Yoruba, French), purpose-built for telco and financial-services contact centres.
AfriHuBERT
AfriHuBERT is a compact self-supervised speech representation model based on mHuBERT-147, continually pretrained via multilingual adaptive finetuning on over 10,000 hours of speech spanning more than 1,200 African languages and varieties. It improves spoken language identification and ASR over its base model and acts as an encoder for downstream African speech tasks. Its training data was aggregated from sources including BibleTTS, Kallaama, NaijaVoices and NCHLT.
Bambara-ASR-v2
Bambara-ASR-v2 is an automatic speech recognition model for Bambara (Bamanankan) fine-tuned from OpenAI's Whisper-large-v2 using parameter-efficient tuning, reaching about 25 percent word error rate. It handles natural Bambara-French code-switching common in Mali's multilingual context. It is released under Apache 2.0 as part of the MALIBA-AI community initiative.
GalsenAI Wolof TTS (xTTS-v2-wolof)
xTTS-v2-wolof is a text-to-speech model for Wolof built by GalsenAI by fine-tuning Coqui's xTTS v2 on the cleaned Anta Women Wolof TTS dataset. It synthesizes Wolof speech and can clone a voice from a reference clip as short as 6 seconds. It was developed by the GalsenAI community in Senegal.
MALIBA-AI Bambara TTS
MALIBA-AI Bambara TTS is a neural text-to-speech model for Bambara (Bamanankan), the most widely spoken language in Mali, built on the Spark-TTS framework with a Qwen2.5-based backbone of around 500M parameters. It supports 10 authentic Bambara speaker voices and outputs 16kHz mono audio without a separate vocoder. It is released under a non-commercial MALIBA-AI research license.
Mbaza Whisper-Small-Kinyarwanda
Whisper-Small-Kinyarwanda is an automatic speech recognition model fine-tuned from OpenAI's Whisper-small on the Common Voice Kinyarwanda dataset, achieving about 24 percent word error rate. It transcribes Kinyarwanda audio into text for speech applications. It was built by Mbaza NLP, part of the Digital Umuganda voice-technology ecosystem in Rwanda.