narrate
Local text-to-speech with multiple engine support.
Install
pip install narrate[kokoro] # Kokoro 82M — fast, runs on CPU
pip install narrate[chatterbox] # Chatterbox 500M — high quality, emotion control
pip install narrate[all] # Both engines + audio playback
Usage
from narrate import narrate
# Uses the best available engine and default voice
narrate("Hello world")
# Choose voice (second positional argument)
narrate("Hello world", "am_adam") # male voice
narrate("Hello world", "bf_emma") # British female
narrate("Hello world", "af_sarah") # soft female
# Keyword style with speed control
narrate("Hello world", voice="af_heart", speed=1.2)
# Chatterbox with emotion control (0.0 = neutral, 1.0 = expressive)
narrate("Hello world", engine="chatterbox", emotion=0.8)
# Save to file without playing
narrate("Hello world", output="hello.wav", play=False)
Available Voices (Kokoro)
| Voice ID | Name | Description |
|---|---|---|
af_heart |
Heart | Female, warm (default) |
af_bella |
Bella | Female, clear |
af_nicole |
Nicole | Female, professional |
af_sarah |
Sarah | Female, soft |
af_sky |
Sky | Female, bright |
am_adam |
Adam | Male, deep |
am_michael |
Michael | Male, natural |
bf_emma |
Emma | British female |
bm_george |
George | British male |
# List all available voices programmatically
from narrate import list_voices
for v in list_voices():
print(f"{v['id']:15} {v['name']:10} {v['description']}")
Engines
| Engine | Params | Speed | Quality | Features |
|---|---|---|---|---|
| Kokoro | 82M | Fast (CPU) | Good | 9 voices, speed control |
| Chatterbox | 500M | Moderate | Excellent | Emotion control, voice cloning |
License
MIT
Metadata
Release files for narrate 0.1.1
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 |
|---|---|---|---|---|
| narrate-0.1.1.tar.gz | 6.7 kB | Without provenance | Details for narrate-0.1.1.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| narrate-0.1.1-py3-none-any.whl | Python 3 | none | any | Details for narrate-0.1.1-py3-none-any.whl |
Total release size: 15.7 kB
Release files / narrate-0.1.1.tar.gz
| Download URL | narrate-0.1.1.tar.gz |
|---|---|
| Size | 6.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
334ede8d3ce93ea9611d32325ca13ab0e1d055202a9fcf40719d38b135656fa3
|
|
BLAKE2b-256 checksum How to use checksums |
2e844d1dcd5886eb1fb7a618ae2e748cd35daf8bd8b02be77aa513e00e554805
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Release files / narrate-0.1.1-py3-none-any.whl
| Download URL | narrate-0.1.1-py3-none-any.whl |
|---|---|
| Size | 9.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
c0704ca771e84329ce5aff88222607d8463262e7ff835f104b09e461ceaf0b04
|
|
BLAKE2b-256 checksum How to use checksums |
091de3082acdff52a9a119d9b238676df369ba1b3949e8f0de25d3791b22e9df
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.3
|
Security for narrate 0.1.1
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.