Generate speech, transcribe audio, and create voice narration with Fish Audio models.
npx skills add https://github.com/refly-ai/refly-skills --skill fish-audio
Please help me install this Agent Skill. Skill: fish-audio Source: https://github.com/refly-ai/refly-skills/tree/main/skills/fish-audio Command: npx skills add https://github.com/refly-ai/refly-skills --skill fish-audio
This Skill automates the creation and processing of audio content, enabling efficient text-to-speech conversion, audio transcription, and voice narration generation.
Use the fish-audio skill to convert the text 'Hello, world!' into speech using the default voice.
High-intent search queries and answers about installing and using this skill.
Audio transcription converts spoken words from provided audio files into written text. You supply the audio file, and the system processes the audio content to extract and output the text transcription.
Yes, voice narration generates high-quality voiceovers from written text. You input your blog post text, and the system outputs an audio version suitable for podcasts or other content applications.
Audio transcription processes provided audio files to convert spoken words into written text. You supply the audio file, and the system extracts the spoken content to output a text transcription.
The text-to-speech model supports specific voice styles for high-quality voice output. You can specify the desired voice style when inputting your text to generate customized audio narration.
Automating audio content creation involves using AI models for text-to-speech conversion, audio transcription, and voice narration generation. This handles both generating audio from text and transcribing audio files into text.
1vesoGenerate speech, transcribe audio/video, and remove backgrounds for HyperFrames compositions.
J-StaR-Films-StudiosAutomate podcast production with text-to-speech, music generation, and audio editing.
smilebank7Translate transcribed lecture text into a target language while preserving timestamps.
Zedit42Generate local speech audio and cloned voices as WAV files.
