Skip to content

feat(speechify): streaming TTS with word-level timestamps via official SDK #6327

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
luke-speechify wants to merge 9 commits into
base: main
Choose a base branch
from
Open

feat(speechify): streaming TTS with word-level timestamps via official SDK #6327

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
032f2c0
feat(speechify): streaming TTS with word-level timestamps via officia…
luke-speechify Jul 6, 2026
75b6c1d
chore: use LiveKit copyright headers to match repo convention
luke-speechify Jul 6, 2026
c008b99
fix(speechify): mark stream start so TTS metrics are emitted
luke-speechify Jul 6, 2026
033ff92
feat(speechify): add simba-3.2 and default to dominic_32 voice
luke-speechify Jul 6, 2026
4a4b546
fix(speechify): restore list_voices, re-raise APIError to avoid mis-r…
luke-speechify Jul 6, 2026
43efeba
chore: keep models.py copyright year at 2024
luke-speechify Jul 13, 2026
5a58f30
Merge branch 'main' into lo/speechify-streaming-tts
luke-speechify Jul 13, 2026
6086cff
fix(speechify): align plugin with speechify-api v3.0.1 (token= auth, …
luke-speechify Jul 13, 2026
fb81a91
fix(speechify): flush per sentence + narrow exception wrapping
luke-speechify Jul 13, 2026
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
22 changes: 12 additions & 10 deletions livekit-plugins/livekit-plugins-speechify/livekit/plugins/speechify/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,26 +14,29 @@

"""Speechify plugin for LiveKit Agents

See https://docs.livekit.io/agents/integrations/tts/speechify/ for more information.
Provides Speechify text-to-speech for LiveKit voice agents. See
https://docs.speechify.ai for API details.
"""

from .models import TTSEncoding, TTSModels
from .tts import DEFAULT_VOICE_ID, TTS, Voice
from livekit.agents import Plugin
from speechify.types.get_voice import GetVoice

from .log import logger
from .models import TTSModels
from .tts import DEFAULT_MODEL, DEFAULT_VOICE_ID, TTS, ChunkedStream, SynthesizeStream
from .version import __version__

__all__ = [
"TTS",
"Voice",
"TTSEncoding",
"ChunkedStream",
"SynthesizeStream",
"GetVoice",
"TTSModels",
"DEFAULT_VOICE_ID",
"DEFAULT_MODEL",
"__version__",
]
Comment thread
luke-speechify marked this conversation as resolved.

from livekit.agents import Plugin

from .log import logger


class SpeechifyPlugin(Plugin):
def __init__(self) -> None:
Expand All @@ -42,7 +45,6 @@ def __init__(self) -> None:

Plugin.register_plugin(SpeechifyPlugin())

# Cleanup docs of unexported modules
_module = dir()
NOT_IN_ALL = [m for m in _module if m not in __all__]

Expand Down
10 changes: 3 additions & 7 deletions livekit-plugins/livekit-plugins-speechify/livekit/plugins/speechify/models.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,18 +11,14 @@
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

from typing import Literal

TTSModels = Literal[
"simba-english",
"simba-multilingual",
]

TTSEncoding = Literal[
"mp3_24000",
"wav_48000",
"ogg_24000",
"aac_24000",
"simba-3.0",
"simba-3.2",
]

VoiceType = Literal["shared", "personal"]
Expand Down
Loading
Loading