From 4857010112b23dcfe01e58f011f1145b85eb17df Mon Sep 17 00:00:00 2001 From: Abhishek Mishra Date: Thu, 20 Aug 2026 14:12:31 +0530 Subject: [PATCH] docs(readme): rebrand the speech surface as Models (was Waves) on the PyPI page The CLI group is 'models' and that's the customer-facing name, so the README top surface, ToC, and section heading now say Models instead of Waves. Code references stay client.waves / smallestai.waves (the actual 5.x SDK attribute; renaming that attribute is a breaking change reserved for 6.0). --- README.md | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/README.md b/README.md index b7c5cb4e..5b32dcd3 100644 --- a/README.md +++ b/README.md @@ -5,8 +5,8 @@ `pip install smallestai` gives you one package with two surfaces, plus a CLI: - **Atoms** — build, configure, deploy, and phone-call voice AI agents (`client.atoms`). -- **Waves** — low-latency text-to-speech and speech-to-text, sync/async and streaming (`client.waves`). -- **CLI** — `smallestai` for managing agents and deploying agent-crew code. +- **Models** — low-latency text-to-speech and speech-to-text, sync/async and streaming (`client.waves`; `smallestai models` in the CLI). +- **CLI** — `smallestai` for managing agents, deploying agent-crew code, and running speech models. ```sh pip install smallestai @@ -15,7 +15,7 @@ pip install smallestai ## Table of Contents - [Quickstart](#quickstart-create-an-agent-and-call-it) -- [Text-to-speech and speech-to-text](#text-to-speech-and-speech-to-text-waves) +- [Text-to-speech and speech-to-text](#text-to-speech-and-speech-to-text-models) - [Agent crew: your own LLM](#agent-crew-your-own-llm-in-the-middle) - [CLI](#cli) - [Async client](#async-client) @@ -48,7 +48,7 @@ client.atoms.calls.start_outbound_call( ) ``` -## Text-to-speech and speech-to-text (Waves) +## Text-to-speech and speech-to-text (Models) `synthesize_tts` streams audio bytes. List available voices with `client.waves.get_voices()`. @@ -170,7 +170,7 @@ except ApiError as e: ## Streaming and websockets -Waves supports real-time, low-latency streaming over websockets. `stream()` returns a context manager; iterate it to process messages as they arrive. +The speech models support real-time, low-latency streaming over websockets. `stream()` returns a context manager; iterate it to process messages as they arrive. ```python from smallestai import SmallestAI