doubao-speech
Skill1 starsChanged 5 months agoMITView on GitHub
Use when needing text-to-speech (TTS) or automatic speech recognition (ASR) using Doubao (豆包) speech models. TTS: convert text to natural speech audio. ASR: transcribe audio to text. Configure API_KEY in .doubao-speech/.env before use.
- Reads credentials
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- content-package-managerSkill
- csdn-publisherSkill
- juejin-publisherSkill
- xiaohongshu-publisherSkill
- zhihu-publisherSkill
- ddd-java-developerSkill
- doubao-videoSkill
- formal-resume-builderSkill
- code-qualitySkill
The file
Files
doubao-speech
Goal
Provide TTS and ASR capabilities using Doubao speech models. Users configure API credentials once, then the AI handles audio generation and transcription.
Configuration
API key must be set before first use:
# In project's .doubao-speech/.env or ~/.doubao-speech/.env
API_KEY=your_api_key_hereModels
| Service | Resource-Id | Description |
| TTS | seed-tts-2.0 | Doubao speech synthesis model 2.0 |
| ASR | volc.seedasr.sauc.duration | Doubao streaming ASR model 2.0 |
Note: These speech models do not support switching via Auto or console.
API Endpoints
TTS (Text-to-Speech):
- Bidirectional streaming (WebSocket):
wss://openspeech.bytedance.com/api/v3/plan/tts/bidirection - Streaming output (WebSocket):
wss://openspeech.bytedance.com/api/v3/plan/tts/unidirectional/stream - HTTP (HTTP POST):
https://openspeech.bytedance.com/api/v3/plan/tts/unidirectional
ASR (Speech Recognition):
- Refer to Doubao ASR documentation for endpoints.
Default Tools
doubao_tts— convert text to speech audio file
Workflow
TTS
- User provides text content and optional voice parameters
- AI reads API_KEY from .doubao-speech/.env
- AI calls doubao_tts tool with text and model settings
- Tool returns audio file path (saved to workspace)
ASR
- User provides audio file
- AI reads ARK_API_KEY from config
- AI processes audio through Doubao ASR service
- Returns transcribed text
Safety Rules
- API keys are read from .doubao-speech/.env only, never hardcoded
- Generated audio files are saved locally, not uploaded anywhere
- User must have ARK_API_KEY configured; tool will fail with clear message if missing
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

