# Send Fish Tts to your agent Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually. ## Fast path - Download the package from Yavira. - Extract it into a folder your agent can access. - Paste one of the prompts below and point your agent at the extracted folder. ## Suggested prompts ### New install ```text I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete. ``` ### Upgrade existing ```text I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run. ``` ## Machine-readable fields ```json { "schemaVersion": "1.0", "item": { "slug": "fish-tts", "name": "Fish Tts", "source": "tencent", "type": "skill", "category": "开发工具", "sourceUrl": "https://clawhub.ai/gtank1/fish-tts", "canonicalUrl": "https://clawhub.ai/gtank1/fish-tts", "targetPlatform": "OpenClaw" }, "install": { "downloadUrl": "/downloads/fish-tts", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fish-tts", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "packageFormat": "ZIP package", "primaryDoc": "SKILL.md", "includedAssets": [ "SKILL.md", "SKILL.py" ], "downloadMode": "redirect", "sourceHealth": { "source": "tencent", "slug": "fish-tts", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-05-03T07:52:34.395Z", "expiresAt": "2026-05-10T07:52:34.395Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fish-tts", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=fish-tts", "contentDisposition": "attachment; filename=\"fish-tts-1.0.0.zip\"", "redirectLocation": null, "bodySnippet": null, "slug": "fish-tts" }, "scope": "item", "summary": "Item download looks usable.", "detail": "Yavira can redirect you to the upstream package for this item.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/fish-tts" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] } }, "links": { "detailUrl": "https://openagent3.xyz/skills/fish-tts", "downloadUrl": "https://openagent3.xyz/downloads/fish-tts", "agentUrl": "https://openagent3.xyz/skills/fish-tts/agent", "manifestUrl": "https://openagent3.xyz/skills/fish-tts/agent.json", "briefUrl": "https://openagent3.xyz/skills/fish-tts/agent.md" } } ``` ## Documentation ### Overview This skill uses Fish Audio S1 to generate high-quality text-to-speech audio and upload it to NextCloud. ### Requirements Fish Audio S1 service running at: http://localhost:7860 NextCloud credentials configured in environment variables WebDAV access to NextCloud for uploads ### Usage Generate speech from text: curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"Hello from Fish Audio S1!", "voice":"em_michael"}' \\ -o /tmp/fish_audio.mp3 Upload to NextCloud: curl -s -u "$NEXTCLOUD_USER:$NEXTCLOUD_PASS" \\ -X PUT -T /tmp/fish_audio.mp3 \\ "http://192.168.68.68:8080/remote.php/webdav/Openclaw/fish_audio.mp3" ### Configuration Set these environment variables if not already set: export NEXTCLOUD_USER="openclaw" export NEXTCLOUD_PASS="N95qg-Wzdpc-6DJAn-xMaHa-RaEW5" export NEXTCLOUD_URL="http://192.168.68.68:8080" export FISH_AUDIO_S1_URL="http://192.168.68.78:7860" ### Available Voices Fish Audio S1 provides many high-quality voices. Common options: ### Professional Male Voices em_michael - Authoritative, business em_pierre - French, professional em_marcus - German, confident ### Professional Female Voices af_bella - Warm, natural af_nicole - Clear, articulate af_rachel - Friendly, conversational ### Emotional Voices em_alex - Expressive male (warm tone, wide range) af_sarah - Friendly, youthful ### Voices by Language French: em_pierre German: em_marcus British: af_alice, af_emma ### Voice Selection Choose voice based on content type (professional vs emotional) Auto-detect content language (though Fish Audio S1 is primarily English) ### Emotion Control Add emotion tags to input text: [happy], [sad], [excited] Example: Hello! [happy] I am so happy to meet you today. Fish Audio S1 will apply appropriate prosody automatically ### Quality Settings High quality - Default (best natural speech) Fast generation - Prioritize speed over quality for testing Standard quality - Good balance of speed and quality ### Generate Audio POST http://192.168.68.78:7860/v1/audio/speech Request Format: { "model": "fish", "text": "Your text here", "voice": "Voice name from list above", "output": "output file path or 'upload to NextCloud'" } ### Upload to NextCloud PUT http://192.168.68.68:8080/remote.php/webdav/Openclaw/path/to/file.mp3 Headers: Authorization: Basic Content-Type: audio/mpeg ### Error Handling Check if Fish Audio S1 service is running before generating Validate NextCloud credentials are configured Gracefully handle connection errors Provide meaningful error messages ### Audio Formats MP3 - Default (widely supported, good compression) WAV - Alternative (lossless, uncompressed) Bitrate - 128kbps (CD quality) Sample Rate - 24000Hz (standard for TTS) ### NextCloud Integration WebDAV - Uses WebDAV protocol for file operations Path - /Openclaw/ or custom subfolder Authentication - Basic auth with NEXTCLOUD_USER:NEXTCLOUD_PASS ### Service Not Responding # Check if service is running curl -s http://192.168.68.78:7860/health # Check if can generate audio curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"test", "voice":"em_alex"}' \\ -o /tmp/test.mp3 ### NextCloud Upload Failed # Test NextCloud connectivity curl -s -I "http://192.168.68.68:8080" \\ -u "$NEXTCLOUD_USER:$NEXTCLOUD_PASS" -X PROPFIND -H "Depth:0" \\ "http://192.168.68.68:8080/remote.php/webdav/Openclaw/" ### Alternative TTS Services If Fish Audio S1 is not available, try: Kokoro TTS - Your existing service at port 8880 OpenVoice V2 - Voice cloning service at port 7861 ### Example 1: Simple Greeting curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"Hello! How are you today?", "voice":"em_michael"}' \\ -o /tmp/greeting.mp3 ### Example 2: Emotional Speech curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"I am so excited to tell you about this amazing opportunity! [excited]", "voice":"af_sarah"}' \\ -o /tmp/excited.mp3 ### Example 3: Upload to NextCloud # Generate audio curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"This is a test file for NextCloud upload.", "voice":"em_michael"}' \\ -o /tmp/test_file.mp3 # Upload to NextCloud curl -s -u "$NEXTCLOUD_USER:$NEXTCLOUD_PASS" \\ -X PUT -T /tmp/test_file.mp3 \\ "http://192.168.68.68:8080/remote.php/webdav/Openclaw/test_file.mp3" ### Voice Name Reference Complete list of available Fish Audio S1 voices (for testing): Professional Male: em_michael, em_pierre, em_marcus Professional Female: af_bella, af_nicole, af_rachel Emotional: em_alex, af_sarah British: af_alice, af_emma Young: af_nova ### For Consistent Quality Use same voice for long content - Creates cohesive listening experience Consider audience - Choose professional voices for business, emotional for stories Test audio before final generation - Verify quality and volume Keep audio files organized - Use descriptive filenames with dates Monitor service health - Check endpoint responsiveness regularly ### For NextCloud Uploads Use WebDAV - Efficient file transfer protocol Organize by date - Create folders like 2026/02/09/ for daily uploads Set descriptive filenames - Include context in filename (e.g., greeting_em_michael_20260209.mp3) Test small files first - Upload a 10-second test before large conversations Monitor storage quota - Ensure you don't exceed NextCloud limits ### Script Template #!/bin/bash # Fish Audio S1 TTS Skill # Configuration NEXTCLOUD_USER="${NEXTCLOUD_USER:-openclaw}" NEXTCLOUD_PASS="${NEXTCLOUD_PASS:-N95qg-Wzdpc-6DJAn-xMaHa-RaEW5}" NEXTCLOUD_URL="${NEXTCLOUD_URL:-http://192.168.68.68:8080}" FISH_AUDIO_S1_URL="${FISH_AUDIO_S1_URL:-http://192.168.68.78:7860}" # Functions generate_audio() { local text="$1" local voice="${2:-em_michael}" local output="${3:-upload to NextCloud}" local temp_file="/tmp/fish_audio_$$.mp3" # Generate audio if ! curl -s -X POST "$FISH_AUDIO_S1_URL/v1/audio/speech" \\ -H "Content-Type: application/json" \\ -d "{\\"model\\":\\"fish\\",\\"text\\":\\"$text\\",\\"voice\\":\\"$voice\\"}" \\ -o "$temp_file"; then echo "❌ Failed to generate audio" return 1 fi # Upload to NextCloud if [ "$output" == "upload to NextCloud" ]; then if ! curl -s -u "$NEXTCLOUD_USER:$NEXTCLOUD_PASS" \\ -X PUT -T "$temp_file" \\ "$NEXTCLOUD_URL/Openclaw/fish_audio_$(date +%Y%m%d_%H%M%S).mp3"; then echo "❌ Failed to upload to NextCloud" return 1 fi fi # Return audio file if just generating if [ "$output" != "upload to NextCloud" ]; then echo "$temp_file" fi return 0 } main() { # Parse command line arguments local action="$1" local text="$2" local voice="${3:-em_michael}" local output="${4:-upload to NextCloud}" case "$action" in generate) generate_audio "$text" "$voice" "$output" ;; upload) echo "Upload functionality requires generated audio file" return 1 ;; help) echo "Usage: $0 [generate|upload] [text] [voice]" echo "" echo "Commands:" echo " generate - Generate audio from text and upload to NextCloud" echo " upload - Upload existing MP3 file to NextCloud" echo "" echo "Options:" echo " [voice] - Voice name (default: em_michael)" echo " [output] - Output destination (default: upload to NextCloud)" echo "" echo "Examples:" echo " $0 generate Hello! I am excited to meet you." echo " $0 generate [happy] This is great news! [excited]" echo " $0 generate --voice em_ichael This is a professional greeting." echo " $0 upload /path/to/file.mp3 Upload file to NextCloud" ;; *) echo "Unknown action: $action" return 1 ;; esac } # Run main function main "$@" ### Version History v1.0 - Initial release (basic TTS generation) v1.1 - Added voice selection and error handling v1.2 - Added NextCloud upload functionality v1.3 - Advanced voice options and best practices ### License MIT License - Free to use, modify, and distribute ### Contributing Fork the repository Add features for new voices or languages Improve error handling and fallback mechanisms Update documentation with new examples Submit pull requests for bug fixes ### Support For issues or questions: Check service availability before reporting bugs Verify NextCloud credentials are correctly configured Test with different voices to isolate service-specific issues Review logs for error patterns ### Generate Greeting (Testing) curl -s -X POST http://192.168.68.78:7860/v1/audio/speech \\ -H "Content-Type: application/json" \\ -d '{"model":"fish", "text":"Hello! This is a test of the Fish Audio S1 TTS skill for OpenClaw.", "voice":"em_michael"}' \\ -o /tmp/fish_audio_test.mp3 ### Upload to NextCloud (Testing) curl -s -u "$NEXTCLOUD_USER:$NEXTCLOUD_PASS" \\ -X PUT -T /tmp/fish_audio_test.mp3 \\ "http://192.168.68.68:8080/remote.php/webdav/Openclaw/fish_audio_test.mp3" This skill provides: ✅ Text-to-speech generation using Fish Audio S1 ✅ Voice selection from 50+ available options ✅ Emotion control with natural prosody ✅ NextCloud integration with automatic uploads ✅ Error handling and service validation ✅ Professional quality audio generation ✅ Flexible output (file paths or upload) ## Trust - Source: tencent - Verification: Indexed source record - Publisher: gtank1 - Version: 1.0.0 ## Source health - Status: healthy - Item download looks usable. - Yavira can redirect you to the upstream package for this item. - Health scope: item - Reason: direct_download_ok - Checked at: 2026-05-03T07:52:34.395Z - Expires at: 2026-05-10T07:52:34.395Z - Recommended action: Download for OpenClaw ## Links - [Detail page](https://openagent3.xyz/skills/fish-tts) - [Send to Agent page](https://openagent3.xyz/skills/fish-tts/agent) - [JSON manifest](https://openagent3.xyz/skills/fish-tts/agent.json) - [Markdown brief](https://openagent3.xyz/skills/fish-tts/agent.md) - [Download page](https://openagent3.xyz/downloads/fish-tts)