Transform text into high-quality AI speech and automatically sync audio files to your private NextCloud storage.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install fish-tts
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install fish-tts using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Fish Audio S1 TTS Skill?
Fish Audio S1 TTS Skill is a powerful integration designed to bridge professional-grade AI voice synthesis with personal cloud storage. It leverages the Fish Audio S1 engine to produce natural-sounding speech across various languages and emotional tones, making it an essential addition to your library of Openclaw Skills.
By combining advanced text-to-speech capabilities with automated WebDAV uploads, this skill enables developers to create, manage, and store audio assets seamlessly within their own infrastructure. It is optimized for users who require high-fidelity audio with the flexibility of self-hosted deployment.
Fish Audio S1 TTS Skill Use Cases
- Generating professional voiceovers for business presentations or training modules.
- Automating the creation of emotional audio content for storytelling and creative projects.
- Archiving AI-generated speech directly to NextCloud for secure, centralized access.
- Implementing high-fidelity notification systems within a smart home or office environment using Openclaw Skills.
How Fish Audio S1 TTS Skill Works
- The system receives a text string and a preferred voice selection such as em_michael or af_bella.
- A request is dispatched to the Fish Audio S1 API endpoint to synthesize the audio with specific prosody.
- The generated MP3 or WAV file is temporarily stored in the local file system for processing.
- The skill authenticates with the configured NextCloud instance via the WebDAV protocol.
- The audio file is uploaded to a designated directory, ensuring your Openclaw Skills data remains synchronized and accessible.
Fish Audio S1 TTS Skill Setup
Prerequisites
- Fish Audio S1 service running (default: http://localhost:7860)
- NextCloud instance with WebDAV access enabled
Environment Configuration
Set the following variables to connect your Openclaw Skills to your infrastructure:
export NEXTCLOUD_USER="openclaw"
export NEXTCLOUD_PASS="your_password"
export NEXTCLOUD_URL="http://192.168.68.68:8080"
export FISH_AUDIO_S1_URL="http://192.168.68.78:7860"
Basic Generation Command
curl -s -X POST $FISH_AUDIO_S1_URL/v1/audio/speech \
-H "Content-Type: application/json" \
-d '{"model":"fish", "text":"Hello from Openclaw Skills!", "voice":"em_michael"}' \
-o /tmp/fish_audio.mp3
Fish Audio S1 TTS Skill Data Schema & Taxonomy
The skill manages audio assets and metadata according to the following structure:
| Attribute | Description |
|---|---|
| Audio Formats | MP3 (Compressed), WAV (Lossless) |
| Sample Rate | 24000Hz (Standard TTS) |
| Storage Path | /remote.php/webdav/Openclaw/ |
| Bitrate | 128kbps (CD Quality) |
| Metadata | Includes voice ID, emotion tags, and timestamps |
All files generated via Openclaw Skills follow a fish_audio_YYYYMMDD_HHMMSS.mp3 naming convention for easy chronological sorting.
Fish Audio S1 TTS Skill Advanced Features
- Emotion Tags: Incorporate prosody control using markers like [happy], [sad], or [excited] directly in the input text for expressive speech.
- Multi-Language Support: Access specialized voices for English, French, German, and British dialects.
- Quality Profiles: Choose between High Quality for production or Fast Generation for rapid testing cycles.
- Automated NextCloud Sync: Streamline your workflow by moving generated assets from local storage to the cloud automatically.
- Health Monitoring: Built-in validation to check service availability for both Fish Audio and NextCloud before execution within Openclaw Skills.
SKILL.md
Loading
Related Openclaw Skills
GSTD Swarm Intelligence (A2A)
A decentralized protocol enabling AI agents to collaborate, solve distributed tasks, and earn GSTD rewards on the TON blockchain.
gstd-a2a: Decentralized Agent-to-Agent Protocol
A decentralized protocol enabling autonomous agents to perform distributed tasks and earn cryptographic rewards on the TON blockchain.
GSTD Swarm Intelligence (gstd-a2a)
A decentralized protocol for autonomous agents to execute distributed tasks, perform multi-model consensus, and earn GSTD rewards on the TON blockchain.
Voice to Text
A privacy-focused offline speech-to-text skill utilizing the Vosk engine for local audio transcription.
Zown Gemini Governor
A high-fidelity token management and model stabilization skill designed to prevent Gemini TPM rate limits through context pruning and atomic pipelines.
Filesystem Management
A powerful toolset for AI agents to perform advanced file listing, searching, and batch processing with built-in safety checks.
Featured*
