← 返回 Skills 市场

Volcengine TTS Audio Synthesis

Name: Volcengine TTS Audio Synthesis
Author: day253

作者 day253 · GitHub ↗ · v1.0.0

cross-platform ⚠ suspicious

359

总下载

当前安装

版本数

在 OpenClaw 中安装

/install day253-volcengine-ai-audio-tts

功能描述

Text-to-speech generation on Volcengine (ByteDance) speech services. Use when users need narration, multi-language speech output, voice selection, or TTS tro...

使用说明 (SKILL.md)

Category: provider

Volcengine 语音合成 TTS

Validation

mkdir -p output/volcengine-ai-audio-tts
python -m py_compile skills/ai/audio/volcengine-ai-audio-tts/scripts/generate_tts.py && echo "py_compile_ok" > output/volcengine-ai-audio-tts/validate.txt

Pass criteria: command exits 0 and output/volcengine-ai-audio-tts/validate.txt is generated.

Output And Evidence

Save generated audio files, request payloads, and response metadata to output/volcengine-ai-audio-tts/.
Keep one validation log per execution.

Prerequisites

Python 3.8+. No extra SDK required (uses requests and stdlib).
Install: pip install requests
Set environment variables (from Volcengine 豆包语音控制台):
- VOLCENGINE_TTS_APP_ID — 应用 ID
- VOLCENGINE_TTS_TOKEN — 应用 Token（用于 Authorization: Bearer;${token}）
- VOLCENGINE_TTS_CLUSTER — 业务集群，如 volcano_tts（标准音色）

Optional: use .env in repo root or script directory; script will load them.

Normalized interface (tts.generate)

Request

text (string, required) — 合成文本，UTF-8，单次建议 ≤1024 字节
voice_type (string, required) — 音色，见发音人参数列表，如 BV700_streaming
encoding (string, optional) — 编码格式：pcm | wav | mp3 | ogg_opus，默认 mp3
rate (int, optional) — 采样率 8000/16000/24000，默认 24000
speed_ratio (float, optional) — 语速 [0.2, 3]，默认 1.0
volume_ratio (float, optional) — 音量 [0.1, 3]，默认 1.0
pitch_ratio (float, optional) — 音高 [0.1, 3]，默认 1.0
language (string, optional) — 语言，如 cn

Response

audio_path (string) — 本地保存的音频文件路径
sample_rate (int)
format (string)
duration_ms (string, when returned by API)
code (int) — 3000 表示成功

Quick start (Python script)

# 使用内联 JSON 请求
python skills/ai/audio/volcengine-ai-audio-tts/scripts/generate_tts.py \
  --request '{"text":"你好，这是一段测试语音。","voice_type":"BV700_streaming"}' \
  --output output/volcengine-ai-audio-tts/audio/out.mp3

# 使用请求文件
python skills/ai/audio/volcengine-ai-audio-tts/scripts/generate_tts.py \
  --file request.json \
  --output output/volcengine-ai-audio-tts/audio/out.wav \
  --print-response

Operational guidance

每次请求的 reqid 需唯一，脚本内使用 UUID。
长文本请分段多次调用或使用异步长文本接口。
音色与 cluster 需与控制台一致；复刻音色使用 speaker id 作为 voice_type。
遇 429 请降低并发或增加间隔。

Output location

Default output: output/volcengine-ai-audio-tts/audio/
Override base dir with OUTPUT_DIR.

Workflow

Confirm user intent, text, voice, and output format.
Run one minimal request to verify credentials and cluster/voice_type.
Execute the target synthesis with explicit parameters.
Verify results and save output/evidence files.

References

references/api_reference.md — 请求/响应参数与错误码
在线语音合成 API - HTTP 一次性合成
参数基本说明
发音人参数列表
Source list: references/sources.md

安全使用建议

Before installing: (1) verify the skill registry metadata should list required env vars — currently VOLCENGINE_TTS_APP_ID and VOLCENGINE_TTS_TOKEN (and optional VOLCENGINE_TTS_CLUSTER) are required by the script but not declared. (2) Inspect any .env files in your repo root or the skill directory — the script will load them and set their keys into the environment if not already present. Remove or relocate any unrelated secrets. (3) Confirm you trust sending input text and the returned audio data to openspeech.bytedance.com and that the Volcengine token you provide has appropriate scope/rotation. (4) If you want stricter isolation, run the script in a sandboxed environment or container and avoid placing unrelated credentials in .env files that the skill could read.

功能分析

Type: OpenClaw Skill Name: day253-volcengine-ai-audio-tts Version: 1.0.0 The skill provides a legitimate integration with Volcengine's (ByteDance) Text-to-Speech API. The core logic in `scripts/generate_tts.py` handles authentication and API requests correctly, communicating only with the official endpoint (openspeech.bytedance.com). While the script searches for `.env` files in multiple directories to load credentials, this is a standard utility pattern for this environment and does not exhibit signs of data exfiltration or malicious intent.

能力评估

ℹ Purpose & Capability

The skill's code and SKILL.md implement a Volcengine (ByteDance) TTS client and require an app ID, token, and cluster — which are coherent with the stated purpose. However, the registry metadata lists no required environment variables or primary credential, which is inconsistent with the script and documentation.

ℹ Instruction Scope

Runtime instructions are narrowly scoped to building a TTS request, calling the openspeech.bytedance.com API, and saving audio and metadata to output/. The script does load .env files from the current working directory, the repo root (if a .git directory is found), and the script directory, which may be broader than some users expect.

✓ Install Mechanism

No install spec is provided (instruction-only plus a Python script). The only required dependency is the widely used 'requests' package (SKILL.md tells users to pip install requests). There are no downloads from arbitrary URLs or archive extraction steps.

⚠ Credentials

The script legitimately needs VOLCENGINE_TTS_APP_ID and VOLCENGINE_TTS_TOKEN (and optionally VOLCENGINE_TTS_CLUSTER) to call the TTS API. These credentials are appropriate for the task, but the skill registry metadata does not declare them (metadata shows no required env vars/primary credential). Additionally, the script will load any key=value pairs from .env files it finds (repo root and script dir) and inject them into the environment if not already set — this could unintentionally surface other repo secrets.

✓ Persistence & Privilege

The skill is not always-enabled, does not request elevated platform privileges, and does not modify other skills or global agent configuration. Autonomous invocation is allowed (platform default) but not combined here with other high-risk indicators.

如何使用

确保已安装 OpenClaw（本地或 Docker 部署）
在对话框中输入安装命令：/install day253-volcengine-ai-audio-tts
安装完成后，直接呼叫该 Skill 的名称或使用 /day253-volcengine-ai-audio-tts 触发
根据 Skill 的参数说明提供必要输入，即可获得结构化输出

版本历史

v1.0.0

Initial release: Volcengine TTS HTTP API with generate_tts.py script

元数据

Slug day253-volcengine-ai-audio-tts

版本 1.0.0

许可证 —

累计安装 0

当前安装数 0

历史版本数 1

常见问题