Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .fern/metadata.json
Original file line number Diff line number Diff line change
Expand Up @@ -45,10 +45,10 @@
}
]
},
"originGitCommit": "ae4a1383eb215784f2c7a4caf3b1c42b6428c516",
"originGitCommit": "c3e8467d7de3ac4b4d54e3c9bc4828bebfc4c792",
"originGitCommitIsDirty": false,
"invokedBy": "ci",
"requestedVersion": "5.2.0",
"requestedVersion": "5.3.0",
"ciProvider": "github",
"sdkVersion": "5.2.0"
"sdkVersion": "5.3.0"
}
10 changes: 8 additions & 2 deletions .fern/replay.lock

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

1 change: 1 addition & 0 deletions .fernignore
Original file line number Diff line number Diff line change
Expand Up @@ -47,3 +47,4 @@ RELEASE.md
# Pre-release verification harness (hand-written)
scripts/**
Makefile
src/smallestai/waves/helpers/**
4 changes: 2 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -128,7 +128,7 @@ from smallestai import SmallestAI
client = SmallestAI(...)

# Connect to the websocket (Sync)
with client.tts.connect() as socket:
with client.speech_to_text.stream() as socket:
# Iterate over the messages as they arrive
for message in socket:
print(message)
Expand All @@ -142,7 +142,7 @@ from smallestai import AsyncSmallestAI
client = AsyncSmallestAI(...)

# Connect to the websocket (Async)
async with client.tts.connect() as socket:
async with client.speech_to_text.stream() as socket:
async for message in socket:
print(message)
```
Expand Down
18 changes: 18 additions & 0 deletions changelog.md
Original file line number Diff line number Diff line change
@@ -1,3 +1,21 @@
## 5.3.0 - 2026-07-28

Unified speech-to-text namespace (breaking), voice cloning, Electron LLM, webhook update.

* **Breaking — unified STT**: legacy `client.waves.transcribe_pulse(...)` and
`client.waves.pulse_stt_streaming(...)` are removed. Use `client.waves.speech_to_text.transcribe(...)`
(file/batch, typed `model` pulse|pulse-pro + `language`) and `client.waves.speech_to_text.stream(...)`
(live WebSocket). The `smallestai.waves.types.transcribe_pulse_*` types are gone. No deprecation alias.
* **Fix — STT/Electron routing**: `speech_to_text.*` and `electron.complete` were generated against the
atoms base and 404'd; both now resolve to the waves base. Live-verified against `api.smallest.ai`.
* **Typed streaming helper** (`from smallestai.waves.helpers import stream_speech_to_text`): typed
handshake params for the full STT param set incl. keyword boosting (`keywords`), redaction, VAD,
diarization; booleans and list params serialized for you; passthrough via `additional_query_parameters`.
* **Additive**: `waves.create_voice_clone` / `list_voice_clones`, `waves.electron.complete`,
`atoms.webhooks.update`.
* Verified live end-to-end against `api.smallest.ai` (batch transcribe, live stream with keyword
boosting, electron completion).

## 5.2.0 - 2026-07-24

Agent Versioning v2 (branch/revision API) + new namespaces, plus an ergonomic versioning helper.
Expand Down
2 changes: 1 addition & 1 deletion pyproject.toml
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ dynamic = ["version"]

[tool.poetry]
name = "smallestai"
version = "5.2.0"
version = "5.3.0"
description = ""
readme = "README.md"
authors = []
Expand Down
Loading
Loading