What is the difference between text to speech and speech to text?
Short answer: Text to speech turns written text into spoken audio; speech to text turns spoken audio into written text.
Side by side
| Text to speech (TTS) | Speech to text (STT) | |
|---|---|---|
| Input | Text | Audio |
| Output | Audio | Text |
| Typical use | Read notifications, prompts, answers | Transcribe calls, voicemails, commands |
| How it is billed | Per character (or tokens or credits) | Per minute or hour of audio |
| Speakvora price | $0.70 per 1M characters (catalog voices) | $0.0015 per minute |
When you need both
A voice assistant listens (speech to text), decides what to say, and answers aloud (text to speech). Speakvora's voice agents do the whole loop for $10 per 1,000 turns (beta); you can also call the two APIs yourself.
Different things to check
- TTS: how the voice sounds, languages, speed for new text.
- STT: accuracy on your audio, languages, formats, whether you need timestamps or speaker labels (Speakvora has neither yet).
Details: text to speech · speech to text · STT price comparison