Book a call

Daniel & Friends / Glossary / Text-to-speech (TTS)

AI and automation

Text-to-speech (TTS)

Text-to-speech (TTS) produces a spoken voice from written text. Current synthetic voices sound natural, handle intonation and often several languages. They are used in voice assistants, audio versions of articles, videos and phone bots.

Daniel Votruba ·


In practice

It is a fast and cheap route for an audio version of an article or a short video. In ads and videos with a voice, make clear that the voice is synthetic.

Related terms

  • Speech-to-text: Speech-to-text, also called automatic transcription, turns spoken words into written text.
  • Voice cloning: Voice cloning creates a synthetic voice that sounds like a specific person, usually from a short recording of their speech.
  • Multimodal model: A multimodal model processes several kinds of input at once, typically text, images, audio or video, and can respond in more than one of them.
  • NLP (natural language processing): NLP, or natural language processing, is the field that lets computers understand and work with human language.

More terms in the group AI and automation

Text-to-video · Text-to-image · Token · Temperature · Vector database · System prompt · Vibe coding · Small language model (SLM) · Agentic AI · Shadow AI · AI agent · Semantic search · AI automation · RPA (robotic process automation) · AI costs and limits · Reasoning model · AI crawlers (GPTBot and others) · RAG (retrieval-augmented generation) · AI governance · Prompt injection · AI personalization · Prompt engineering · AI safety and alignment · Prompt

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.