Speed

speed sets how fast the voice speaks, from 0.7 (slower) to 1.3 (faster). 1, the default, is the voice’s natural pace. Any number in the range works, such as 0.85 or 1.1.

`speed`	Use it for
`0.7` to `0.9`	Learners, dense instructions, numbers and names that must be caught the first time
`1`	Most text
`1.1` to `1.3`	Short notifications, previews, listeners who already know the content

curl https://api.aderra.ai/v1/audio/speech \
  -H "Authorization: Bearer $ADERRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "aderra-voice-1", "voice": "Reid",
       "input": "Take the second exit, then turn left.", "speed": 0.85}' \
  --output slow.mp3

audio = client.audio.speech.create(
    model="aderra-voice-1",
    voice="Reid",
    input="Take the second exit, then turn left.",
    speed=0.85,
)
audio.write_to_file("slow.mp3")

const audio = await client.audio.speech.create({
  model: 'aderra-voice-1',
  voice: 'Reid',
  input: 'Take the second exit, then turn left.',
  speed: 0.85,
});
fs.writeFileSync('slow.mp3', Buffer.from(await audio.arrayBuffer()));

A speed outside 0.7 to 1.3, or one that is not a number, is refused with 400 invalid_speed. OpenAI accepts 0.25 to 4, so code written for OpenAI may need its value brought into range.
Speed does not change the price: you pay for the characters, not the seconds of audio.
GET /v1/audio/models gives the range as data[0].speed: {"min": 0.7, "max": 1.3, "default": 1}.