Fish Audio
Converts text to speech using Fish Audio's API with support for multiple voice models, streaming, and various audio formats.
10690 views8Local (stdio)
What it does
- Generate speech from text using AI voice models
- Stream audio in real-time for low-latency applications
- Select voices by ID, name, or tags from voice library
- Export audio in multiple formats (MP3, WAV, PCM, Opus)
- Clone and create custom voice models
- Control speech prosody and emotions
Best for
Building conversational AI applicationsAutomated content narration and voiceoversCreating multilingual speech synthesisReal-time voice generation for chatbots
Multilingual supportReal-time streaming capabilityVoice cloning features
