This release is a pre-release and may not be stable for production use.
swarmauri_tts_gemini_dialogue
Alpha Swarmauri GeminiDialogueTTS component. Speaker-labelled Interactions turns, separate from single-speaker Gemini TTS.
Features
- Structured multi-voice files, async synthesis, streams and bounded batches.
- Provider-specific schemas and local input validation.
- Fixed provider endpoints and no automatic replay of billable requests.
- Python 3.10-3.14; no swarmauri_standard dependency.
Installation
uv add --prerelease allow swarmauri_tts_gemini_dialogue
pip install --pre swarmauri_tts_gemini_dialogue
This source candidate needs swarmauri_base>=0.11.0.dev12 published first.
Usage
import os
from swarmauri_tts_gemini_dialogue import GeminiDialogueTTS, GeminiDialogueTurn
provider = GeminiDialogueTTS(
api_key=os.environ["GEMINI_API_KEY"],
speaker_voices={"Joe": "Puck", "Jane": "Kore"},
)
turns = (
GeminiDialogueTurn(text="How are you?", speaker="Joe", style="cheerful"),
GeminiDialogueTurn(text="Doing well!", speaker="Jane"),
)
path = provider.predict(turns, "dialogue.wav")
# await provider.apredict(turns, "dialogue.wav")
# provider.batch({turns: "dialogue.wav"})
# await provider.abatch({turns: "dialogue.wav"}, max_concurrent=2)
# Iterate provider.stream(turns), or async-iterate provider.astream(turns).
API boundary
This package uses Gemini 3.8 Interactions with separate speaker-labelled text items and speech_config.speakers. Bind exactly two speaker labels to voice names or already-provisioned IDs. Every turn must reference a bound speaker. Turn styles override the optional global style. Tuples of frozen turns can be used as batch keys. Strings require default_speaker, which must be bound; that mode can be used by TextToSpeechAgent. The single-speaker voice setting is not accepted by this component. JSON strings are not parsed into turns.
Models are gemini-3.8-flash-tts and gemini-3.8-flash-lite-tts. The existing swarmauri_tts_gemini package supplies JSON WAV decoding and SSE raw PCM decoding. Files are WAV; streams are headerless pcm_s16le, 24 kHz mono and require the interaction.completed event. store=false is preserved. Old generateContent previews, Gemini Live and voice management are excluded.
Primary reference: multi-speaker speech.
Verification and alpha status
Live API behavior is unverified; tracked in #6308. No paid synthesis was run. Retain version 0.1.0a1 and Development Status :: 3 - Alpha until maintainers review sufficient live evidence. Mocked schemas do not prove playable audio, model availability, voice controls, quality, latency or cost.
Live tests require SWARMAURI_LIVE_TTS=1 plus private GEMINI_API_KEY. The live suite defaults to Puck/Kore; use SWARMAURI_TTS_VOICE and SWARMAURI_TTS_SECOND_VOICE for account-accessible alternatives. Select the model with SWARMAURI_TTS_MODEL. A key alone never enables the suite. Default selection is predict only (one billable request). SWARMAURI_LIVE_TTS_OPERATIONS selects a comma-separated operation list. All six operations make eight billable requests per model. Never paste credentials or unmasked headers into issues or logs. See the verification tracker.
License
Apache-2.0. Part of the Swarmauri SDK.
Metadata
Release files for swarmauri_tts_gemini_dialogue 0.1.0a1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| swarmauri_tts_gemini_dialogue-0.1.0a1.tar.gz | 8.8 kB | Without provenance | Details for swarmauri_tts_gemini_dialogue-0.1.0a1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| swarmauri_tts_gemini_dialogue-0.1.0a1-py3-none-any.whl | Python 3 | none | any | Details for swarmauri_tts_gemini_dialogue-0.1.0a1-py3-none-any.whl |
Total release size: 19.3 kB
Release files / swarmauri_tts_gemini_dialogue-0.1.0a1.tar.gz
| Download URL | swarmauri_tts_gemini_dialogue-0.1.0a1.tar.gz |
|---|---|
| Size | 8.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
19cf1bf603eb0a83a124bf76588306b6f47259b7ca458ba0e9fa8540ed9a7090
|
|
BLAKE2b-256 checksum How to use checksums |
97ff85c640031743ebe7e3a18be0f1a79266c0129e0a8673b47d51b274c61abe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Release files / swarmauri_tts_gemini_dialogue-0.1.0a1-py3-none-any.whl
| Download URL | swarmauri_tts_gemini_dialogue-0.1.0a1-py3-none-any.whl |
|---|---|
| Size | 10.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
51088ad22aa9c34685fbe703f999f667b5044034e402b4bc785fdfa3e812f9ac
|
|
BLAKE2b-256 checksum How to use checksums |
d65808a8e5fd700724cbcbc990108a3ac91b7d8769ea8b82086dd516360f3d3a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.13.9 {"installer":{"name":"uv","version":"0.13.9","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"Ubuntu","version":"24.04","id":"noble","libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":true}
|
Security for swarmauri_tts_gemini_dialogue 0.1.0a1
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.