Python Quick Start

This guide shows the current setup for the wfloat Python package.

1. Install

pip install wfloat

2. Load the model

The Python package is free to use however you want. It does not require a Wfloat modelId or model credential. Load the public wfloat/wfloat-tts model directly:

import wfloat

model = wfloat.load("wfloat/wfloat-tts")

The first load downloads the model assets. After that, the package uses the cached local copy.

3. Generate speech

import wfloat

model = wfloat.load("wfloat/wfloat-tts")

result = model.generate(
    text="No, no, that's not possible. The formula should have crystallized, but it adapted instead. Do you realize what that means for the rest of my work?",
    voice_id="mad_scientist_woman",
    emotion="surprise",
    intensity=0.7,
)

result.audio.save("out.wav")

4. Generate dialogue

import wfloat

model = wfloat.load("wfloat/wfloat-tts")

result = model.generate_dialogue(
    segments=[
        {
            "voice_id": "wise_elder_man",
            "text": "Rain taps against the tavern shutters as you step inside.",
            "emotion": "neutral",
            "intensity": 0.5,
        },
        {
            "voice_id": "strong_hero_man",
            "text": "You're late. Two bandits stole the king's map over three hours ago.",
            "emotion": "fear",
            "intensity": 0.6,
        },
        {
            "voice_id": "strong_hero_man",
            "text": "They fled north, up into the woods.",
            "emotion": "neutral",
            "intensity": 0.5,
        },
    ],
    silence_between_segments_sec=0.35,
)

result.audio.save("dialogue.wav")

5. Use the CLI

You can also generate a WAV from the command line:

wfloat generate \
  --text "Hello world!" \
  --out out.wav \
  --voice-id mad_scientist_woman \
  --emotion surprise \
  --intensity 0.7 \
  --silence-padding-sec 0

For full CLI help:

wfloat generate --help

6. Voice IDs

Use voice_id string names or numeric sid values:

Speaker	SID
skilled_hero_man	0
skilled_hero_woman	1
fun_hero_man	2
fun_hero_woman	3
strong_hero_man	4
strong_hero_woman	5
mad_scientist_man	6
mad_scientist_woman	7
clever_villain_man	8
clever_villain_woman	9
narrator_man	10
narrator_woman	11
wise_elder_man	12
wise_elder_woman	13
outgoing_anime_man	14
outgoing_anime_woman	15
scary_villain_man	16
scary_villain_woman	17
news_reporter_man	18
news_reporter_woman	19

7. Emotions

Supported emotion labels:

• neutral
• joy
• sadness
• anger
• fear
• surprise
• dismissive
• confusion

intensity must be between 0.0 and 1.0.