Voice Transcribe
Transcribe audio files using OpenAI's gpt-4o-mini-transcribe model with vocabulary hints and text replacements. Requires uv (https://docs.astral.sh/uv/).
clawhub install voice-transcribeConvert text into natural and fluent speech audio using OpenAI TTS
# Install Skill (downloads SKILL.md to .claude/skills/) clawhub install openai-tts # Then just tell Claude: "use OpenAI TTS to help me..."
# Same install command — works with all SKILL.md-compatible AI coding tools clawhub install openai-tts
This Skill is compatible with the OpenClaw standard. After installation, a SKILL.md file is auto-generated, usable by any OpenClaw-compatible AI Agent (Claude Code, Cursor, Windsurf, etc.).
/v1/audio/speech endpoint.{baseDir}/scripts/speak.sh "Hello, world!"
{baseDir}/scripts/speak.sh "Hello, world!" --out /tmp/hello.mp3
tts-1 (fast) or tts-1-hd (quality)alloy (neutral), also: echo, fable, onyx, nova, shimmermp3{baseDir}/scripts/speak.sh "Text" --voice nova --model tts-1-hd --out speech.mp3
{baseDir}/scripts/speak.sh "Text" --format opus --speed 1.2
--voice <name>: alloy|echo|fable|onyx|nova|shimmer (default: alloy)--model <name>: tts-1|tts-1-hd (default: tts-1)--format <fmt>: mp3|opus|aac|flac|wav|pcm (default: mp3)--speed <n>: 0.25-4.0 (default: 1.0)--out <path>: output file (default: stdout or auto-named)OPENAI_API_KEY, or configure in ~/.clawdbot/clawdbot.json:{
skills: {
entries: {
"openai-tts": {
apiKey: "sk-..."
}
}
}
}
#!/usr/bin/env python3
# OpenAI TTS 完整示例
from openai import OpenAI
import os
client = OpenAI(api_key=os.getenv('OPENAI_API_KEY'))
# 转换文本列表为语音
texts = [
"这是第一段文案",
"这是第二段文案",
"欢迎订阅我们的频道"
]
voices = ['alloy', 'echo', 'fable'] # 不同声音选项
for i, text in enumerate(texts):
response = client.audio.speech.create(
model="tts-1-hd", # 高质量模型
input=text,
voice=voices[i % len(voices)],
response_format="mp3"
)
output_file = f"audio_{i+1}.mp3"
response.stream_to_file(output_file)
print(f"✓ 已生成: {output_file}")
print("\n所有音频生成完成!")Create chapters, highlights, and show notes from podcast audio or transcripts. Use when a user wants chapter markers, highlight clips, or show-note drafts without publishing or distribution actions.
clawhub install podcast-chaptering-highlights