How do I control pitch and speed in a speech synthesis API?

In most speech synthesis APIs, speed and pitch are exposed as separate parameters in the request, or via SSML tags.

Common controls

1) Speed / rate

Controls how fast the text is spoken.

• Typical names: rate, speed, speakingRate
• Example values: 0.5 = slower, 1.0 = normal, 1.5 = faster

2) Pitch

Controls how high or low the voice sounds.

• Typical names: pitch
• Example values: -5, 0, +5 semitones, or a percentage depending on the API

Example JSON-style request

{
  "text": "Hello world",
  "voice": "en-US-Standard-A",
  "speed": 1.1,
  "pitch": 2
}

Example with SSML

Many APIs support SSML, which lets you wrap speech settings around text:

<speak>
  <prosody rate="1.1" pitch="+2st">
    Hello world
  </prosody>
</speak>

• rate="1.1" means slightly faster
• pitch="+2st" means 2 semitones higher

Notes

• APIs differ in the accepted range and units.
• Some use:
  • rate as a multiplier
  • pitch in semitones
  • speed as a percentage
• Very high/low values can make speech sound unnatural or fail validation.

If you tell me which API you’re using, I can show the exact parameters and an example call.