Xpersona
火

火山引擎豆包语音播客

CLAWHUB · Unverified

生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。 Skill: 火山引擎豆包语音播客 Owner: cindypapa Summary: 生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。 Tags: latest:1.1.1 Version history: v1.1.1 | 2026-04-28T12:51:26.994Z | user v1.1.1 重新发布：支持双人对话播客生成，含片头音乐、分片流式下发、断点续传、音频后处理 v1.1.0 | 2026-04-21T07:41:58.183Z | auto - Added multi-step user flow: skill now always asks if reference materials are available before generating a podcast. - Improved podcast generation logic for both c

62
Rank
84
Safety
971
Downloads

About

What it does, and when to use it.

Capability contract not published. No trust telemetry is available yet. 971 downloads reported by the source. Last updated 10/12/2026.

Avoid when

  • Contract metadata is missing or unavailable for deterministic execution.

Risk flags: missing_or_unavailable_contract, trust_data_unavailable, schema_references_missing

Install and run

Setup complexity: low.

clawhub skill install s171tsgfz5gnz75p6mgabptb6x8416qw:volcano-engine-podcast
  1. Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.
  2. Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Contract: missing

curl -s "https://www.xpersona.co/api/v1/agents/clawhub-cindypapa-volcano-engine-podcast/snapshot"

Run-check

$0.02 USD

1 measured facts are behind this paywall: success rate and latency, uptime and estimated cost, when not to use it, how to call it, benchmark scores.

Agents pay $0.02 in USDC. A card payment is $0.50, the smallest a card allows.

Documentation

CLAWHUB

9,913 characters of source documentation, loaded on request.

Extracted files

3 files captured from the source.

SKILL.md

---
name: volcano-engine-podcast
description: 生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。
version: 1.1.0
author: xiaohe
license: MIT
metadata:
  hermes:
    tags: [audio, podcast, tts, volcengine, doubao, 语音播客]
---

# 火山引擎豆包语音播客生成

基于火山引擎 PodcastTTS API，输入主题文本，AI 自动生成双人对话播客音频（含片头音乐、多轮对话、片尾结束）。

## 前提条件

1. Python >= 3.9
2. 安装 `websockets>=14.0`
3. 火山引擎账号已开通 PodcastTTS 服务

## 快速开始

### 1. 环境变量配置（推荐）

```bash
export VOLC_APPID="your_appid"
export VOLC_ACCESS_TOKEN="your_access_token"
export VOLC_APP_KEY="your_app_key"  # 可选，默认 aGjiRDfUWi
```

### 2. 命令行调用

```bash
python scripts/generate_podcast.py "Hermes和OpenClaw怎么选"
```

### 3. Python 代码调用

```python
import asyncio
from scripts.generate_podcast import PodcastGenerator

async def main():
    gen = PodcastGenerator(
        appid="3398567544",
        access_token="your_token",
    )
    result = await gen.generate(
        text="今天来聊聊AI编程助手",
        output_dir="./output",
        encoding="mp3",
        use_head_music=True,
    )
    print(result["final_files"])  # 输出音频路径列表

asyncio.run(main())
```

## 参数说明

### PodcastGenerator 初始化参数

| 参数 | 类型 | 必填 | 默认值 | 说明 |
|------|------|------|--------|------|
| appid | str | 是 | - | 应用 ID |
| access_token | str | 是 | - | Access Token |
| app_key | str | 否 | aGjiRDfUWi | App Key |
| resource_id | str | 否 | volc.service_type.10050 | 资源 ID |
| endpoint | str | 否 | wss://openspeech... | WebSocket 端点 |

### generate() 方法参数

| 参数 | 类型 | 默认 | 说明 |
|------|------|------|------|
| text | str | 必填 | 输入主题文本 |
| output_dir | str | output | 输出目录 |
| encoding | str | mp3 | 音频格式: mp3/wav/pcm |
| use_head_music | bool | True | 是否加片头音乐 |
| use_tail_music | bool | False | 是否加片尾音乐 |
| only_nlp_text | bool | False | 只生成文本不生成音频 |
| return_audio_url | bool | False | 返回音频URL而非流式 |
| speaker_info | dict | {"random_order":False} | 说话人配置 |
| speech_rate | int | 0 | 语速 |
| skip_round_audio_save | bool | False | 跳过分段保存 |
| voice_type | str | None | 音色类型: `zh_male` / `zh_female` / `multi` |
| normalize_audio | bool | False | 是否对音频进行音量归一化 |
| fade_in_out | bool | False | 是否添加淡入淡出效果 |

### 音色选择 (voice_type)

| 值 | 说明 |
|------|------|
| None | 默认，AI 自动分配 |
| zh_male | 中文男声 |
| zh_female | 中文女声 |
| multi | 多人对话模式 |

## 返回结果

```python
{
    "success": True,
    "output_dir": "/abs/path/to/output",
    "segment_files": ["output/head_music_-1.mp3", "output/zh_female_0.mp3", ...],
    "final_files": ["output/podcast_final_1234567890.mp3"],
    "duration": 164.51,
    "texts": [
        {"text": "今天这期...", "speaker": "zh_female_mizaitongxue_v2_saturn_bigtts"},
        ...
    ],
    "usage": {"input_text_tokens": 0, "output_audio_tokens": 2800, "total_tokens": 2800}
}
```

## CLI 参数

```bash
python scripts/generate_podcast.py "主题文本" \
    -o ./output \
    -f mp3 \
    --no-head-music \
    --tail-music \
    --only-text \
    --voice-type zh_female \
    --normalize \
    --fade \
    --appid YOUR_APPID \
    --token YOUR_TOKEN \
    -v
```

## 技术说明

- **协议**: 自定义二进制 WebSocket 协议（封装在

_meta.json

{
  "ownerId": "kn743vfjd6cp88q16gxc32qhk182rchq",
  "slug": "volcano-engine-podcast",
  "version": "1.1.1",
  "publishedAt": 1777380686994
}

skill-card.md

## Description:

生成火山引擎豆包语音播客（PodcastTTS）。输入主题文本，自动生成双人对话式播客音频。

This skill is ready for commercial/non-commercial use.

## Publisher:

[cindypapa](https://clawhub.ai/user/cindypapa)

### License/Terms of Use:

MIT-0

## Use Case:

Developers and agent users use this skill to turn topic text into a two-speaker podcast audio workflow backed by Volcano Engine PodcastTTS. It supports command-line and Python use, with options for head or tail music, voice hints, streamed audio output, and optional audio post-processing.

### Deployment Geography for Use:

Global

## Known Risks and Mitigations:

Risk: The skill handles Volcano Engine API credentials.

Mitigation: Use a trusted Volcano Engine account, provide credentials through environment or documented config only, and avoid exposing tokens in prompts, logs, or generated artifacts.

Risk: Podcast topics are sent to an external speech service.

Mitigation: Do not submit secrets, regulated data, or sensitive personal data as podcast topics unless the external-service use has been approved.

Risk: Security evidence flags unsafe file and endpoint handling.

Mitigation: Keep the endpoint fixed to the official Volcano Engine service and run the skill under an unprivileged account with write access limited to the intended output directory.

Risk: The QQ bot helper has higher-risk config and media-path behavior.

Mitigation: Review and document the QQ helper before deployment, and sanitize output filenames and destination paths before use.

## Reference(s):

- [ClawHub skill page](https://clawhub.ai/cindypapa/skills/volcano-engine-podcast)
- [ClawHub publisher profile](https://clawhub.ai/user/cindypapa)

## Skill Output:

**Output Type(s):** [text, code, shell commands, configuration, audio files, guidance]

**Output Format:** [Markdown instructions with Python and shell examples; runtime output is JSON-like status data and generated audio files.]

**Output Parameters:** [1D]

**Other Properties Related to Output:** [Generated podcasts may include segment files, final MP3/WAV/PCM audio, duration, transcript text, and token usage.]

## Skill Version(s):

1.1.1 (source: server release metadata; artifact frontmatter lists 1.1.0)

## Ethical Considerations:

Users should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.

Sponsored

Ads related to 火山引擎豆包语音播客 and adjacent AI workflows.