Workshops Use Cases Architecture Projects Blog
About Contact Offers Talks
Home›AI technologies›Text to speechDeutsch

Text to speech: written text read out loud

Neural text-to-speech turns text into natural-sounding audio, in many languages and voices, and can tell you when each word is spoken.

Amazon PollyAzure AI SpeechText-to-SpeechP
Book a free 30-min call →AI Concept and Prototype workshops →

What is text to speech?

A speech synthesis model reads text aloud. You can mark up the text to control pauses, emphasis and pronunciation, usually with SSML, and many services return the timing of every word so you can highlight text as it is read.

A custom voice built from your own recordings is possible on the big platforms, and it is a larger commitment, legally as well as technically.

Goes inText, optionally marked up for pauses and emphasis
Comes outAn audio file, and the timing of every word if you ask
Typical usesVoice assistants, accessibility, e-learning, phone systems

Four ways to run it

Each of the big clouds offers it as a managed service, and you can also run it yourself. Same task, a different bill and a different console.

Amazon Polly
Managed on AWS

Amazon Polly[1]

The managed text-to-speech service on AWS, with neural voices in many languages and speech marks for word timings.

Official documentation →
Azure AI Speech
Managed on Microsoft Azure

Azure AI Speech[2]

The managed speech service on Microsoft Azure; text to speech is one of its features, including custom voices.

Official documentation →
Text-to-Speech
Managed on Google Cloud

Text-to-Speech[3]

The managed speech synthesis API on Google Cloud.

Official documentation →
P
Run it yourself

Piper[4]

A fast open-source speech synthesis engine that runs on your own machine. Development moved from the archived rhasspy/piper repository to OHF-Voice/piper1-gpl, which is GPL-3.0.

Project page →
Amazon Polly: The managed service on one page, with the same service on the other platforms.
The managed service on one page, with the same service on the other platforms.[5]

How it looks in an architecture

Slides from my course on AI architectures at FH Burgenland, drawn from real projects.

Five ready-made AI services, the technology underneath each one, and what it is called elsewhere.
Five ready-made AI services, the technology underneath each one, and what it is called elsewhere.[6]
When a ready-made service is the right start, and when to look further down.
When a ready-made service is the right start, and when to look further down.[6]

Where I used it

Text to speech is not part of my three reference projects, and that is deliberate: most internal tools are read, not listened to. A service existing is not a reason to use it.

Managed and self-hosted together: hybrid

With a ready-made service the call leaves your network. The hybrid decision is what crosses, and in what state: the whole file, a redacted one, or only the part that has to. Where a file may not leave at all, the same step runs with the open-source option inside your building, and only the result, or nothing, crosses.[7]

Hybrid is a decision at every layer. For text to speech the question is which text may be sent out to be read.
Hybrid is a decision at every layer. For text to speech the question is which text may be sent out to be read.[8]

What would help you next?

Learn to decide

The course “From Managed to Hybrid” teaches where AI should run: what each layer costs, what you operate and where your data has to stay. It is in preparation, with a free live session first.

Join the course waitlist →
Linda MohamedLinda Mohamed
AI and cloud consultant, AWS Community Hero, Vienna

Build it with me

Tell me what you want to build. In 30 minutes we check which of the four ways fits your data, your rules and your budget, and whether AWS funding for a proof of concept can cover part of it. How AWS funding works →

Book a free 30-min call →15-min question slot

You already know what you need

Book the workshop directly:

ai-solutions.wiki

Read more on ai-solutions.wiki

My open knowledge base, with longer comparisons, pricing notes and sources.

Sources

  1. Amazon Polly documentation. https://docs.aws.amazon.com/polly/latest/dg/what-is.html
  2. Azure AI Speech documentation. https://learn.microsoft.com/en-us/azure/ai-services/speech-service/text-to-speech
  3. Text-to-Speech documentation. https://cloud.google.com/text-to-speech/docs
  4. Piper. https://github.com/OHF-Voice/piper1-gpl
  5. Linda Mohamed, course slides “The projects”, MASE-3, FH Burgenland, September 2026
  6. Linda Mohamed, course slides “How to run AI, layer by layer”, MASE-3, FH Burgenland, September 2026
  7. NIST glossary: hybrid cloud. https://csrc.nist.gov/glossary/term/hybrid_cloud
  8. Linda Mohamed, course slides “Start here”, MASE-3, FH Burgenland, September 2026
  9. Amazon Polly, ai-solutions.wiki. https://ai-solutions.wiki/tools/amazon-polly/
  10. Azure Speech Services, ai-solutions.wiki. https://ai-solutions.wiki/tools/azure-speech-services/
  11. Pre-built AI services vs foundation models, ai-solutions.wiki. https://ai-solutions.wiki/comparisons/prebuilt-ai-services-vs-foundation-models/
  12. rhasspy/piper, archived repository. https://github.com/rhasspy/piper

Links checked September 2026. Product names and features change: check the linked pages before you decide.