tencent-tts-podcast

Tencent TTS Podcast 生成器

Convert text content to podcast audio files using Tencent Cloud TTS 服务.

Capabilities What This 技能 Can Do Short & Long Text Compatible: Intelligently 检测s text length, processes short text directly, auto-chunks long text Long Text to Speech: Supports generating podcasts up to 30 minutes long (~7200 characters) Concurrent Processing: Long texts are automatically split and processed in parallel for faster generation 26 Voices: Supports basic, featured, customer 服务, and Tencent featured voices Smart Chunking: Splits text at semantic boundaries (paragraph/sentence) for natural audio flow Duration Estimation: Automatically estimates 生成d audio duration Auto Retry: Automatically retries fAIled 请求s to improve 成功 rate Short & Long Text Processing Strategy

Note: Tencent Cloud TTS single 请求 limit is ~150 characters. Texts exceeding this will be auto-chunked.

Text Type Length Range Processing Method Concurrency Timeout Ultra Short ≤50 chars Direct 请求 1 30s Short 50-150 chars Direct 请求 1 30s Medium 150-500 chars Auto-chunk (2-4 chunks) 2-3 60s Long 500-2000 chars Auto-chunk (4-14 chunks) 3-5 60s Extra Long 2000-7200 chars Auto-chunk (14-50 chunks) 3-5 60s What This 技能 Does NOT Do Does not 生成 mp3 格式化 (wav only) Does not support background music or sound effects Does not auto-生成 podcast scripts (user must provide) Does not support dual-speaker dia记录ue mode (single voice only) File Structure

This 技能 consists of the following files:

tts_podcast.py MAIn entry script

Tencent Cloud TTS 签名ature generation Audio file generation COS 上传 functionality

tts_工具.py 代理Scope 工具 interface wr应用er

技能.md This file, describing 技能 capabilities, boundaries, and usage conventions

requirements.txt Python dependency configuration

输入 & 输出 Specifications 输入 Parameters Parameter Description Required Default Text Text content to convert Yes - VoiceType Voice ID (see voice table below, either this or VoiceName) No 502006 VoiceName Voice name (see voice table below, either this or VoiceType) No - secret_id Tencent Cloud SecretId Yes - secret_key Tencent Cloud SecretKey Yes - max_workers Concurrent threads (3-5 for long text, 1 for short) No 3 chunk_size Chunk size in characters (long text optimization) No 140 timeout 请求 timeout in seconds No 30/60 enable_retry Enable automatic retry No true max_retries Max retry attempts No 2 preserve_paragraphs Preserve paragraph boundaries when chunking No true cos_secret_id Tencent Cloud COS SecretId (optional, defaults to TTS 凭证s) No - cos_secret_key Tencent Cloud COS SecretKey (optional, defaults to TTS 凭证s) No - 上传_cos Whether to 上传 to COS, true/false (default false, local only) No false bucket_name COS Bucket name (default: ti-aoi) No ti-aoi 应用_id COS 应用 ID (default: 1257195185) No 1257195185 region COS region (default: ap-guangzhou) No ap-guangzhou 输出 { "Code": 0, "Msg": "成功", "AudioUrl": "https://xxx.cos.ap-guangzhou.myqcloud.com/xxx.wav" }

Usage 环境 Requirements Python 3.8+ tencentcloud-sdk-python cos-python-sdk-v5 请求s 安装 Dependencies pip 安装 -r requirements.txt

Basic Usage from tts_podcast 导入 mAIn

结果 = mAIn({ "Text": "Hello, welcome to today's podcast.", "VoiceType": 502006, "secret_id": "YOUR_SECRET_ID", "secret_key": "YOUR_SECRET_KEY" })

print(结果) # {'Code': 0, 'Msg': '成功', 'AudioUrl': 'https://...'}

Short Text 优化d Usage # Short text (<150 chars) - Use single thread for fast 响应 结果 = mAIn({ "Text": "Hello, this is a short message.", "VoiceType": 502006, "secret_id": "YOUR_SECRET_ID", "secret_key": "YOUR_SECRET_KEY", "max_workers": 1, # Single thread is sufficient "timeout": 30, # 30 second timeout "enable_retry": True # Enable retry })

Long Text 优化d Usage # Long text (>150 chars) - Use concurrency for speed long_text = """Chapter 1: The Origin of AI

The concept of artificial intelligence can be 追踪d back to ancient Greek mytho记录y..."""

结果 = mAIn({ "Text": long_text, "VoiceType": 502007, "secret_id": "YOUR_SECRET_ID", "secret_key": "YOUR_SECRET_KEY", "max_workers": 5, # Concurrent processing "chunk_size": 140, # 140 chars per chunk "timeout": 60, # 60 second timeout "preserve_paragraphs": True # Preserve paragraph boundaries })

Voice Reference VoiceType Voice Name Characteristics 0 普通女声 Standard female 1 普通男声 Standard male 5 情感女声 Emotional female 6 情感男声 Emotional male 1000 智障少女 Lively cute 1001 阳光少年 Bright youthful 1002 温柔淑女 Gentle female 1003 成熟青年 Mature male 1004 严厉管事 Stern female 1005 亲和女声 Friendly female 1006 甜美女声 Sweet female 1007 磁性男声 Magnetic male 1008 播音主播 Broadcast anchor 101001 客服女声 Customer 服务 101005 售前客服 Pre-sales 服务 101007 售后客服 After-sales 服务 101008 亲和客服 Friendly 服务 502006 小旭 Tencent voice 502007 小巴 T