Speech Model API

This page has been superseded by the new Text-to-Speech (TTS) documentation.

Please refer to Text-To-Speech (TTS) API for the current shared interfaces (TextToSpeechModel and StreamingTextToSpeechModel).

The old provider-specific classes (SpeechModel, StreamingSpeechModel, SpeechPrompt, SpeechResponse) have been removed in favor of shared interfaces that work across all TTS providers (OpenAI, ElevenLabs, and future providers).

Redirects

For general TTS documentation: Text-To-Speech (TTS) API
For OpenAI-specific documentation: OpenAI Text-to-Speech
For ElevenLabs-specific documentation: ElevenLabs Text-to-Speech
For migration guide: Migration Guide