FineVoice TTS voices are powered by Fish Audio. You can embed emotion tags directly in your text to control how the voice sounds.
Usage
Wrap a tag name in square brackets and insert it in your text field. Each tag applies to the text that follows it until the next tag (or end of string).
Tag names are case-insensitive. [Happy], [HAPPY], and [happy] are all equivalent.
Best Practices
Follow these guidelines to get the most natural-sounding output:
1. Place tags at the start of a sentence
Tags work best when placed at the beginning of a sentence or a natural pause point, not mid-sentence or mid-word.
2. Match the tag to the content
Choose a tag that reflects the actual meaning of the sentence. Mismatched emotion and content will produce awkward or unnatural output.
3. Do not stack multiple tags consecutively
Placing two or more tags back-to-back without any text between them is not supported and may cause unexpected behavior. Use one tag per sentence or paragraph.
4. Use one tag per logical segment
A single tag should cover one sentence or one short paragraph. Avoid switching tags too frequently — this can make the speech sound unnatural.
Basic Emotions
Advanced Emotions
Tone Markers
Audio Effects
These tags insert a natural human sound instead of modifying spoken text.
Special Effects
Aliases
The following aliases are accepted and map to the corresponding canonical tag: