Provider Index
A one-page map of every OpenTypeless provider configuration guide. Use this page to jump directly to the provider you want.
STT Providers
Deepgram Nova-3
Low-latency streaming with broad language support.
/docs/stt-deepgram
AssemblyAI
Streaming transcription with turn formatting.
/docs/stt-assemblyai
OpenAI Whisper
Whisper API via HTTP transcription endpoint.
/docs/stt-openai-whisper
Groq Whisper
OpenAI-compatible Whisper endpoint optimized for speed.
/docs/stt-groq-whisper
Zhipu GLM-ASR
GLM ASR endpoint with OpenAI-like request shape.
/docs/stt-glm-asr
SiliconFlow STT
SenseVoiceSmall via SiliconFlow audio API.
/docs/stt-siliconflow
Aliyun Qwen3-ASR
DashScope WebSocket real-time ASR.
/docs/stt-aliyun-qwen3-asr
Volcengine Doubao ASR
ByteDance OpenSpeech bigmodel streaming ASR.
/docs/stt-volcengine-doubao
LLM Providers
OpenAI
Default: gpt-4o-mini on /v1/chat/completions.
/docs/llm-openai
DeepSeek
Default: deepseek-chat via compatible API.
/docs/llm-deepseek
Claude (via OpenRouter)
Recommended Claude route in OpenTypeless.
/docs/llm-claude
Gemini
Google OpenAI-compatible endpoint for Gemini models.
/docs/llm-gemini
Groq
Fast inference through Groq OpenAI-compatible API.
/docs/llm-groq
Zhipu
GLM chat completion endpoint.
/docs/llm-zhipu
Moonshot (Kimi)
Moonshot OpenAI-compatible API.
/docs/llm-moonshot
Qwen (DashScope)
Alibaba DashScope OpenAI-compatible mode.
/docs/llm-qwen
SiliconFlow
OpenAI-compatible chat completions.
/docs/llm-siliconflow
Ollama (Local)
Local runtime with OpenAI-compatible endpoint.
/docs/llm-ollama
OpenRouter
Unified multi-model routing layer.
/docs/llm-openrouter
Recommended Order for New Users
- Pick one STT provider with easy key issuance (Deepgram or AssemblyAI).
- Pick one LLM provider with stable low-cost usage (DeepSeek or OpenAI).
- Complete both connection tests before changing advanced options.
- After baseline works, benchmark alternatives and switch providers without changing workflow.