skills.rest
riipandi
riipandiCOMMUNITY
Explore all skills by this author →
Website𝕏@riipandiGitHub

doubao-tts

Convert text to audio files using the Volcengine Doubao TTS V3 SSE streaming API.

1|Updated Jun 20, 2026
Search Tags:#voice#audio generation#tts#speech synthesis#volcengine#doubao#text to speech
One-click install
npx skills add https://github.com/riipandi/minis-skills --skill doubao-tts-riipandi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: doubao-tts
Source: https://github.com/riipandi/minis-skills/tree/main/doubao-tts
Command: npx skills add https://github.com/riipandi/minis-skills --skill doubao-tts-riipandi

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve? It turns written text into playable audio files without manual recording, using Volcengine's Doubao speech synthesis service with configurable voices, emotions, and speech rates. ## Core Features & Use Cases - Text-to-Speech Synthesis: Calls the Doubao TTS V3 HTTP SSE unidirectional streaming API to generate MP3, PCM, or OGG Opus audio files. - Voice and Emotion Control: Supports multiple Chinese and English voices across seed-tts-1.0 and seed-tts-2.0 models, plus emotion and speech-rate tuning. - Dual Authentication: Works with either the new console API Key or legacy AppID plus Access Token credentials. - Use Case: A user asks to read an article aloud; the skill runs the bundled tts.py script and returns a playable MP3 link in the workspace. ## Quick Start Ask the assistant to convert a piece of text into an audio file with Doubao TTS, optionally naming a voice or emotion, after setting the DOUBAO_TTS_API_KEY environment variable.

Frequently Asked Questions about doubao-tts

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert text to speech with Doubao TTS?▼

Run the bundled tts.py script with --text and --output arguments after setting the DOUBAO_TTS_API_KEY environment variable. The script calls the Volcengine V3 SSE streaming endpoint and saves the synthesized audio as an MP3 file by default.

What voices does Volcengine Doubao speech synthesis support?▼

The seed-tts-2.0 model supports *_uranus_bigtts voices such as zh_female_shuangkuaisisi and en_female_dacey, while seed-tts-1.0 supports BV*_streaming voices. Voices from the two model generations cannot be mixed.

Can I use Doubao TTS with an API Key instead of AppID and Token?▼

Yes, the new Volcengine console API Key is the recommended authentication method and takes precedence over the legacy AppID plus Access Token pair. Set DOUBAO_TTS_API_KEY or pass --api-key to the script.

Why does Doubao TTS return server error code 55000000?▼

This error usually means the selected voice does not match the Resource ID generation. Use seed-tts-2.0 for *_uranus_bigtts voices and seed-tts-1.0 for BV*_streaming voices, or retry if it is a transient server issue.

What audio formats and speech rates does Doubao TTS support?▼

Supported output formats are mp3, pcm, and ogg_opus, with sample rates from 8000 to 48000 Hz. Speech rate ranges from -50 to 100, where 100 is double speed and -50 is half speed.

Related Skills

Explore More Content & Communication Skills→
hackeshackeshackeshackes
6

podcast-generation

Convert written text into a two-host conversational podcast MP3.

Community
Intermediate
yudameyudame
2

podcast-audio-processing

Convert podcast audio to MP3, transcribe locally with Whisper, and embed chapter metadata.

Official
Intermediate
valentinuuiuiuvalentinuuiuiu

whisper

Transcribe audio into text across 99 languages and translate to English.

Community
Advanced
jieni777jieni777
1

aliyun-tts

Convert text to speech via Alibaba Cloud TTS with configurable voice, format, and sample rate.

Community
Advanced