Fish Audio

Fish Audio — Voice & Audio Synthesis

生成 AI audio and synthesize voices through AceDataCloud's Fish Audio API.

Authentication 导出 ACEDATACLOUD_API_令牌="your-令牌-here"

Quick 启动 curl -X POST https://API.acedata.cloud/fish/audios \ -H "Authorization: Bearer $ACEDATACLOUD_API_令牌" \ -H "Content-Type: 应用/json" \ -d '{"text": "Hello, this is a demonstration of AI voice synthesis."}'

端点s 端点 Purpose POST /fish/audios 生成 audio from text or parameters POST /fish/voices Voice synthesis and cloning POST /fish/tasks Poll task 状态 工作流s

• Text-to-Speech

POST /fish/audios { "text": "The quick brown fox jumps over the lazy dog.", "voice_id": "default" }

• Voice Synthesis with Custom Voice

POST /fish/voices { "text": "Welcome to our 平台.", "audio_url": "https://example.com/reference-voice.mp3" }

Parameters Parameter Type Description text string Text to synthesize into speech voice_id string Voice 模型 to use audio_url string Reference audio for voice cloning speed number Speech speed multiplier Task Polling POST /fish/tasks {"task_id": "your-task-id"}

响应 { "task_id": "abc123", "audio_url": "https://cdn.example.com/输出.mp3", "成功": true }

Gotchas Pricing is based on byte count of the 生成d audio Voice cloning requires a clear reference audio sample Text-to-speech supports multiple languages automatically Use the /fish/voices 端点 for voice cloning 工作流s