/fal-audio
Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.
$ npx -y skills add refly-ai/refly-skills --skill fal-audio --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/fal-audio
Context preview
The summary Claude sees to decide when to auto-load this skill.
Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.
SKILL.md
fal-audio.SKILL.mdname: fal-audio
description: "Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples."
version: 1.0.0
skillId: skp-rp9vuflwd7rbpz69qpes5b7q
workflowId: c-jpzyxwna765lcz547405kpa8
installationId: skpi-f2vbjqtn7q295d2ttuqve6uz
category: file-generation
Fal Audio
Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.
Input
Provide input as JSON:
{
"text_content": "The text content to convert to speech. Can be a script, article, or any text you want to vocalize.",
"audio_type": "Type of audio to generate: 'speech' for simple text-to-speech, 'podcast' for conversational style, or 'clone' for voice cloning",
"voice_style": "Voice characteristics or style preferences (e.g., 'professional male', 'warm female', 'energetic narrator')",
"reference_audio": "<file-reference>"
}Execution (Pattern A: File Generation)
Step 1: Run the Skill and Get Run ID
RESULT=$(refly skill run --id skpi-f2vbjqtn7q295d2ttuqve6uz --input '{
"text_content": "Hello, welcome to our podcast.",
"audio_type": "speech",
"voice_style": "professional male"
}')
RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
# RUN_ID is we-xxx format, use this for workflow commandsStep 2: Open Workflow in Browser and Wait for Completion
open "https://refly.ai/workflow/c-jpzyxwna765lcz547405kpa8"
refly workflow status "$RUN_ID" --watch --interval 30000
Step 3: Download and Show Result
# Get files from this run
FILES=$(refly workflow toolcalls "$RUN_ID" --files --latest | jq -r '.payload.files[]')
# Download and open each file
echo "$FILES" | jq -c '.' | while read -r file; do
FILE_ID=$(echo "$file" | jq -r '.fileId')
FILE_NAME=$(echo "$file" | jq -r '.name')
if [ -n "$FILE_ID" ] && [ "$FILE_ID" != "null" ]; then
refly file download "$FILE_ID" -o "$HOME/Desktop/${FILE_NAME}"
open "$HOME/Desktop/${FILE_NAME}"
fi
doneExpected Output
- **Type**: Audio
- **Format**: .mp3/.wav audio file
- **Location**: `~/Desktop/`
- **Action**: Opens automatically to show user
Rules
Follow base skill workflow: `~/.claude/skills/refly/SKILL.md`
Read more
name: fal-audio description: "Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples." version: 1.0.0 skillId: skp-rp9vuflwd7rbpz69qpes5b7q workflowId: c-jpzyxwna765lcz547405kpa8 installationId: skpi-f2vbjqtn7q295d2ttuqve6uz category: file-generation
Fal Audio
Generate AI audio using Fal.ai audio models. Use when you need to: (1) convert text to natural speech, (2) create podcast-style audio content, or (3) clone voices from audio samples.
Input
Provide input as JSON:
{
"text_content": "The text content to convert to speech. Can be a script, article, or any text you want to vocalize.",
"audio_type": "Type of audio to generate: 'speech' for simple text-to-speech, 'podcast' for conversational style, or 'clone' for voice cloning",
"voice_style": "Voice characteristics or style preferences (e.g., 'professional male', 'warm female', 'energetic narrator')",
"reference_audio": "<file-reference>"
}Execution (Pattern A: File Generation)
Step 1: Run the Skill and Get Run ID
RESULT=$(refly skill run --id skpi-f2vbjqtn7q295d2ttuqve6uz --input '{
"text_content": "Hello, welcome to our podcast.",
"audio_type": "speech",
"voice_style": "professional male"
}')
RUN_ID=$(echo "$RESULT" | jq -r '.payload.workflowExecutions[0].id')
# RUN_ID is we-xxx format, use this for workflow commandsStep 2: Open Workflow in Browser and Wait for Completion
open "https://refly.ai/workflow/c-jpzyxwna765lcz547405kpa8" refly workflow status "$RUN_ID" --watch --interval 30000
Step 3: Download and Show Result
# Get files from this run
FILES=$(refly workflow toolcalls "$RUN_ID" --files --latest | jq -r '.payload.files[]')
# Download and open each file
echo "$FILES" | jq -c '.' | while read -r file; do
FILE_ID=$(echo "$file" | jq -r '.fileId')
FILE_NAME=$(echo "$file" | jq -r '.name')
if [ -n "$FILE_ID" ] && [ "$FILE_ID" != "null" ]; then
refly file download "$FILE_ID" -o "$HOME/Desktop/${FILE_NAME}"
open "$HOME/Desktop/${FILE_NAME}"
fi
doneExpected Output
- **Type**: Audio
- **Format**: .mp3/.wav audio file
- **Location**: `~/Desktop/`
- **Action**: Opens automatically to show user
Rules
Follow base skill workflow: `~/.claude/skills/refly/SKILL.md`
Repo: refly-ai/refly-skills
Other skills on refly-skills.
airtable
Integrate with Airtable for database management. Use when you need to: (1) create and query…
alpha-vantage
Get financial data from Alpha Vantage. Use when you need to: (1) retrieve stock quotes and…
apollo
Search sales leads with Apollo.io. Use when you need to: (1) find company and contact…

