Voice, language, and video AI

Abena AI

Speak, create, and build in African languages.

Use Akan Twi, Ghanaian Pidgin, and English for hands-free phone control, smart home commands, speech recognition, natural voices, and multilingual video creation.

Try Speech Recognition Try Text to Speech

500K+Android installs

WSA 2025Global winner

OfflineVoice assistance

Abena products

Choose the experience you need

Try the browser playgrounds, integrate through the REST API, or use Abena AI directly on Android.

Android app

Voice Assistant and Smart Home

Control your phone, connected home, calls, messages, weather, airtime, and everyday tasks by voice, including offline commands.

Get Abena AI

ASR

Speech Recognition

Transcribe Akan Twi with English code-switching, Twi-only speech, Ghanaian Pidgin, and English from a microphone or audio file.

Open ASR Playground

TTS

Text to Speech

Turn text into natural speech with supported African-language, regional English, and Pidgin voices through the web or API.

Open TTS Playground

Creative AI

Multilingual Video Creation

Create music videos, studio sessions, video podcasts, drama, and dubbed content using African and global voices in the mobile app.

Create on Android

Abena AI offline Akan Twi voice assistant screen

Abena AI local-language media creation options

Abena AI mobile app

One app for voice, smart home, and local-language creation

Abena is designed for daily use, not only demonstrations. Speak to your phone, control compatible smart-home devices, complete common tasks, and create media without leaving the app.

Hands-free phone and app control
Smart-home voice commands
Mobile money, airtime, and bill actions
Calls, messages, news, weather, and voice notes
Music videos, podcasts, studio sessions, and drama

For developers and teams

Ship African-language speech features with a simple REST API

Evaluate models in the browser, then use the documented TTS and ASR endpoints from Python, JavaScript, mobile apps, or your existing backend.

POST /playground/api/v1/tts/synthesize/

POST /playground/api/v1/asr/transcribe/

Read API Documentation Explore Playgrounds

Speech Recognition Playground

Text-to-Speech Playground

Flexible deployment

Cloud when you need it. On device when you do not.

Hosted APIs

Integrate quickly without managing speech infrastructure.

On-device AI

Run supported voice experiences locally without an internet connection.

Private by design

Keep supported audio and voice interactions on the user's device.

Proprietary data

Built with native speakers and real recording workflows

Our team works with voice artists, language reviewers, and audio engineers to create and evaluate speech data for languages often underserved by mainstream technology.

Native-speaker studio recording
Language review and quality control
Training and evaluation across real use cases

Abena AI voice artists recording proprietary speech data in a studio

Inside our speech-data recording process

Recognition

Recognized for African-language innovation

Explore independent coverage and international recognition of Abena AI.

Global award World Summit Awards Winner 2025 View recognition Featured on BBC Watch feature Featured in TechCabal Read coverage Featured in Voicebot.ai Read coverage Featured in MyJoyOnline Read coverage Featured in Yen.com.gh Read coverage

Where Abena fits

Language technology for real products and services

Customer experience

Local-language support, voice agents, and call transcription.

Education and accessibility

Spoken learning content, literacy tools, and accessible interfaces.

Finance and field work

Hands-free workflows, voice-enabled services, and local-language guidance.

Media and entertainment

Natural voices, podcasts, music videos, drama, and localized content.

Work with Abena AI

Build the next African-language experience

Start in the playground or contact us about APIs, on-device deployment, data, and partnerships.

Contact the Team Read the Docs