Gandr TTS from Python.
The official package. Zero dependencies, streaming and retry built in, one constructor line.
Ask Claude Code
Ask ChatGPTThe whole integration
Install and call. The key lives in your environment.
pip install gandr
from gandr import Gandr
g = Gandr("gnd_...") # or read GANDR_API_KEY
g.say("Hello from Gandr.")
Python 3.9 or newer, no other packages. Streaming, prewarm and retry are inside the client, so a cold call does not fail.
What it needs
What it takes
| One package | pip install gandr |
| A key | Pass gnd_... or set GANDR_API_KEY |
| Python | 3.9 or newer |
| Dependencies | None |
Why the package exists
The client is the surface a Python team meets first. Zero dependencies means one install and no version fights, and streaming, prewarm and retry are inside the client so a cold call does not fail on a first request.
The constructor takes a key or reads GANDR_API_KEY from the environment. The say method returns playable audio, and the streaming surface returns chunks as they render.
What the flat stream changes
Python backs a lot of batch work: narration, dubbing pipelines, agent loops. On a per-character meter those jobs bill by volume; on a flat stream the bill is the stream, and long render jobs stop being a cost line to avoid.
- One stream carries batch and streaming work alike
- No per-character meter on long narration jobs
- Retry and prewarm are built in, not bolted on
Notes
Do I need to install anything besides gandr?
No. The package is zero dependency. Python 3.9 or newer is the only requirement.
Can I stream audio as it renders?
Yes. The same constructor exposes a streaming surface that returns chunks as they are synthesized.