Fish Audio Drama 3 text to speech: direct each line with emotions, whispers and laughs in brackets, thousands of voices, 80+ languages. In IIshki Studio.
Fish Audio Voiceover is available in IIshki Studio — audio generation from a prompt, paid for with tokens. IIshki club members get reduced prices on every model. Pick a model above, set the parameters and start the generation.
Fish Audio is a text-to-speech model you can direct line by line: write how to perform a line in square brackets (whispering, smiling, holding back tears) and Drama 3 delivers it that way. IIshki Studio gives you thousands of voices from the open Fish Audio library in 80+ languages, output as MP3 or WAV.
Open Fish Audio in IIshki Studio, paste up to 5,000 characters, pick a voice from the library (filter by language, gender and style) and press Create. In a few seconds you get an audio file to download, and it also arrives in Telegram if it is linked.
Put directions in square brackets before the words they apply to: [whispering], [sarcastic], [holding back tears]. Sounds and pauses work the same way: [laughs], [sigh], [pause]. The editor also has buttons for emotions, sounds and pauses.
Yes. Copy the voice ID or a fish.audio/m/… link and paste it into the search box of the voice picker: the voice shows up in the list, ready to preview and select. Public voices from the Fish Audio library work.
Drama 3 is the most expressive model and follows performance directions best. S2.1 Pro is faster and cheaper, also reads emotion tags, but plays it more restrained. Use Drama 3 for ads and characters, S2.1 Pro for long narration.
The price depends on text length and is shown in tokens on the model card. You can buy tokens without a subscription.