Speech
Turn audio into text or text into audio.
Create speech
client.audio.speech.create(SpeechCreateParams { input, model, voice, 4 more } body, RequestOptionsoptions?): Response
POST/audio/speech
Search the API docs
Suggested
Primary navigation
Suggested
Get started
Core concepts
Agents
- Overview
-
Build agents
-
Deploy in your product
-
Optimize
- Voice agents
Tools
- Using tools
- Web search
- MCP and Connectors
- Skills
- Shell
- Computer use
-
File search and retrieval
- Tool search
-
More tools
Run and scale
- Conversation state
- Background mode
- Streaming
- WebSocket mode
- Webhooks
- File inputs
-
Context management
-
Prompting
-
Reasoning
Realtime API
Model optimization
Specialized models
Going live
- Production best practices
-
Latency optimization
-
Cost optimization
- Accuracy optimization
Legacy APIs
-
Assistants API