Yiga AI

Speech & Vision with AI APIs

Connect transcription, text-to-speech and image understanding through APIs.

IntermediateNewCertificate

New courseUpdated October 2026English

Part of AI Engineer (LLM Applications) · Course 12 of 13

Included with Yiga Plus

  • Pay with MTN MoMo, Airtel Money, M-Pesa or card
  • Learn on phone, laptop or WhatsApp
  • Certificate of completion
  • Downloadable lessons for low data
Training 5 or more people? Get Yiga for Business

What you'll learn

  • Set up API requests for speech and image tasks.
  • Transcribe audio using Whisper and check the output for errors.
  • Generate spoken audio from text with a TTS API.
  • Submit images with prompts to an image-understanding API.
  • Test language support and output quality for Luganda and Swahili.
  • Handle API errors and protect API credentials.
  • Build a project that combines speech and image API calls.

Skills you'll gain

Speech transcriptionText-to-speechImage understandingAPI integrationMultilingual testingOutput evaluation

This course includes

  • 14h of video
  • 16 lessons
  • 4 quizzes
  • 1 project
  • AI tutor
  • Certificate of completion
  • Mobile and offline access

Curriculum

4 modules · 21 lessons · 14h total
  • Overview and set-up40m
  • Core concepts40m
  • Worked example40m
  • Hands-on practice40m
  • Module quiz: Whisper20m

Projects

Graded project: Speech & Vision with AI APIs

Apply everything from Speech & Vision with AI APIs in one graded, portfolio-ready build.

Requirements

  • Basic programming and familiarity with API requests and responses are required.
  • A laptop or desktop with a code editor and internet access.
  • Access to the API services used in the lessons; check provider credentials, usage limits and charges.

Description

Speech & Vision with AI APIs is an intermediate course for developers who already understand basic programming and API requests. It introduces Whisper, text-to-speech and image understanding as parts of an application workflow. It is not a first programming course. Explore how audio and image inputs are submitted to a service and how an application handles the response. Practise working with transcription output, generated speech and image interpretations, paying attention to errors and the limits of a model's answer. Consider how input quality, usage limits and service costs affect the usefulness of a feature. Keep credentials private and use audio or images you have permission to process. Combine the course techniques in a project that demonstrates a speech or vision workflow and explains what its output can and cannot establish. Transcriptions and image descriptions need checking; they should not be treated as certain evidence or professional diagnosis. Provider access and pricing can change, so confirm the services available to you before beginning the exercises.

Who this course is for

  • Developers adding audio or image features to web and mobile apps.
  • Computing students ready to move beyond basic API requests.
  • Education technology builders exploring spoken learning tools.
  • Developers in Uganda, Kenya, Tanzania, Rwanda, and Nigeria working on multilingual applications.

Career outcomes

Frequently asked questions

Will I receive a certificate?

Check the course details or contact support to confirm whether a certificate is available and what completion requirements apply.

How long will I have access to the course?

Check the access terms shown before enrolment. Contact support if the access period is unclear.

Can I study offline or with limited data?

The API exercises need an internet connection. Check whether course materials are available for offline use. For lower-data practice, use short audio clips and smaller images where the API allows.

Can I pay with MTN MoMo, Airtel Money, M-Pesa, or a card?

Check checkout for the payment methods available in your country, including whether MTN MoMo, Airtel Money, M-Pesa, or card payments are offered. Contact support if your preferred method is not listed.

How do I request a refund?

Contact support to ask about refunds and the policy that applies to your enrolment.

Related courses

LLMs for Developers cover illustration
AI

17 lessons · 14.1h · Intermediate

LLMs for Developers

APIs (OpenAI, Anthropic, Gemini), Tokens & cost, Streaming, and more.

Yiga Plus
Building AI Agents cover illustration
AI

24 lessons · 19.3h · Intermediate

Building AI Agents

Tool use, Planning, Memory, and more.

Yiga Plus

Speech & Vision with AI APIs

Included with Yiga Plus