Agent Skills
› davepoon/buildwithclaude
› ops-voice
ops-voice
GitHub提供语音操作能力，包括通过Bland AI拨打电话、使用ElevenLabs进行文本转语音以及利用Groq Whisper转录音频。支持从配置或环境变量自动解析API密钥，无需SDK依赖。
Trigger Scenarios
需要拨打语音电话时
需要将文本转换为语音文件时
需要转录音频文件内容时
Install
npx skills add davepoon/buildwithclaude --skill ops-voice -g -y
SKILL.md
Frontmatter
{
"name": "ops-voice",
"description": "Voice operations — make phone calls (Bland AI), text-to-speech (ElevenLabs), transcribe audio (Whisper\/Groq). Replace OpenClaw voice capabilities.",
"allowed-tools": [
"Bash",
"Read",
"Write",
"AskUserQuestion",
"WebFetch"
],
"argument-hint": "[call|tts|transcribe|setup]"
}
OPS:VOICE — Voice Operations
Voice interface commands. All API calls via curl — no SDK dependencies.
Credential resolution order: userConfig → env vars → Doppler MCP tools (mcp__doppler__*) → Doppler CLI fallback (doppler secrets get <KEY> --plain) → password manager
Sub-commands
Parse $ARGUMENTS for the command keyword, then execute:
call [phone] [prompt] — Bland AI phone call
Requires: bland_ai_api_key in userConfig or BLAND_AI_API_KEY env or Doppler.
BLAND_KEY="${BLAND_AI_API_KEY:-$(doppler secrets get BLAND_AI_API_KEY --plain 2>/dev/null || true)}"
PHONE="<extracted from $ARGUMENTS>"
PROMPT="<extracted from $ARGUMENTS or ask user>"
MAX_DURATION="${BLAND_MAX_DURATION:-300}" # seconds
VOICE="${BLAND_VOICE:-male}"
# Make the call
RESPONSE=$(curl -s -X POST "https://api.bland.ai/v1/calls" \
-H "authorization: $BLAND_KEY" \
-H "Content-Type: application/json" \
-d "{
\"phone_number\": \"$PHONE\",
\"task\": \"$PROMPT\",
\"voice\": \"$VOICE\",
\"max_duration\": $MAX_DURATION,
\"record\": true
}")
CALL_ID=$(echo "$RESPONSE" | python3 -c "import json,sys; print(json.load(sys.stdin).get('call_id',''))" 2>/dev/null)
# Poll for completion (up to 5 min)
if [ -n "$CALL_ID" ]; then
echo "Call initiated: $CALL_ID"
for i in $(seq 1 30); do
sleep 10
STATUS=$(curl -s "https://api.bland.ai/v1/calls/$CALL_ID" \
-H "authorization: $BLAND_KEY" | \
python3 -c "import json,sys; d=json.load(sys.stdin); print(d.get('status',''), d.get('transcripts','')[-1].get('text','') if d.get('transcripts') else '')" 2>/dev/null)
echo "Status: $STATUS"
[[ "$STATUS" == completed* ]] && break
done
fi
Output: Call ID, live status, transcript when complete.
tts [text] [--voice voice_id] [--out file.mp3] — ElevenLabs text-to-speech
Requires: elevenlabs_api_key in userConfig or ELEVENLABS_API_KEY env or Doppler.
EL_KEY="${ELEVENLABS_API_KEY:-$(doppler secrets get ELEVENLABS_API_KEY --plain 2>/dev/null || true)}"
VOICE_ID="${ELEVENLABS_VOICE_ID:-21m00Tcm4TlvDq8ikWAM}" # Rachel (default)
TEXT="<extracted from $ARGUMENTS>"
OUT_FILE="${OUT_FILE:-/tmp/ops-tts-$(date +%s).mp3}"
# List voices if voice name provided (not an ID)
# Synthesize
curl -s -X POST "https://api.elevenlabs.io/v1/text-to-speech/${VOICE_ID}" \
-H "xi-api-key: $EL_KEY" \
-H "Content-Type: application/json" \
-d "{
\"text\": \"$TEXT\",
\"model_id\": \"eleven_monolingual_v1\",
\"voice_settings\": {\"stability\": 0.5, \"similarity_boost\": 0.75}
}" \
--output "$OUT_FILE"
echo "Audio saved to: $OUT_FILE"
# Auto-play on macOS
command -v afplay &>/dev/null && afplay "$OUT_FILE" &
Output: Audio file path. Auto-plays on macOS via afplay.
transcribe [file_path] — Groq Whisper transcription
Requires: groq_api_key in userConfig or GROQ_API_KEY env or Doppler.
GROQ_KEY="${GROQ_API_KEY:-$(doppler secrets get GROQ_API_KEY --plain 2>/dev/null || true)}"
AUDIO_FILE="<extracted from $ARGUMENTS>"
if [ ! -f "$AUDIO_FILE" ]; then
echo "ERROR: File not found: $AUDIO_FILE"
exit 1
fi
TRANSCRIPT=$(curl -s -X POST "https://api.groq.com/openai/v1/audio/transcriptions" \
-H "Authorization: Bearer $GROQ_KEY" \
-F "file=@$AUDIO_FILE" \
-F "model=whisper-large-v3" \
-F "response_format=json" | \
python3 -c "import json,sys; print(json.load(sys.stdin).get('text',''))" 2>/dev/null)
echo "$TRANSCRIPT"
Output: Transcript text printed to stdout.
setup — Configure voice API keys
Before asking for anything, auto-scan ALL sources in a single background batch:
# Env vars
printenv BLAND_AI_API_KEY BLAND_API_KEY ELEVENLABS_API_KEY GROQ_API_KEY 2>/dev/null
# Shell profiles
grep -h 'BLAND\|ELEVENLABS\|GROQ' ~/.zshrc ~/.bashrc ~/.zprofile ~/.envrc 2>/dev/null | grep -v '^#'
# Doppler — ALL projects
for proj in $(doppler projects --json 2>/dev/null | jq -r '.[].slug'); do
for cfg in dev stg prd; do
doppler secrets --project "$proj" --config "$cfg" --json 2>/dev/null | \
jq -r --arg proj "$proj" --arg cfg "$cfg" 'to_entries[] | select(.key | test("BLAND|ELEVENLABS|GROQ"; "i")) | "\(.key)=\(.value.computed | .[0:12])... (doppler:\($proj)/\($cfg))"'
done
done
# Dashlane
dcli password bland --output json 2>/dev/null | jq -r '.[] | select(.password != null) | "\(.title): key found"'
dcli password elevenlabs --output json 2>/dev/null | jq -r '.[] | select(.password != null) | "\(.title): key found"'
dcli password groq --output json 2>/dev/null | jq -r '.[] | select(.password != null) | "\(.title): key found"'
# Keychain
security find-generic-password -s "bland-ai-api-key" -w 2>/dev/null
security find-generic-password -s "elevenlabs-api-key" -w 2>/dev/null
security find-generic-password -s "groq-api-key" -w 2>/dev/null
Present all findings. Only prompt for keys NOT found in any source. Then validate each found key in background:
- Bland AI:
curl -s -H "authorization: $KEY" https://api.bland.ai/v1/me— check balance - ElevenLabs:
curl -s -H "xi-api-key: $KEY" https://api.elevenlabs.io/v1/voices?page_size=1— list voices - Groq:
curl -s -H "Authorization: Bearer $KEY" https://api.groq.com/openai/v1/models— list models
Report: [service] ✓ connected or [service] ✗ invalid key — [error]
Execution
- Resolve the sub-command from
$ARGUMENTS(first word: call / tts / transcribe / setup) - Resolve credentials in order: env → Doppler
- Execute the matching curl block above
- If a required key is missing and
setupwas not invoked, suggest/ops:ops-voice setup
Version History
- 502fc01 Current 2026-07-05 15:11
