Skip to content

Commit

Permalink
wording changes suggested by mods
Browse files Browse the repository at this point in the history
  • Loading branch information
rayan-saleh committed May 20, 2023
1 parent 1f91eb8 commit 84e5b70
Show file tree
Hide file tree
Showing 6 changed files with 8 additions and 7 deletions.
2 changes: 1 addition & 1 deletion mint.json
Original file line number Diff line number Diff line change
Expand Up @@ -48,7 +48,7 @@
"voicelab/overview",
"voicelab/pre-made-voices",
"voicelab/voice-design",
"voicelab/voice-cloning" ]
"voicelab/instant-voice-cloning" ]
},
{
"group": "Speech Synthesis",
Expand Down
2 changes: 1 addition & 1 deletion speech-synthesis/models.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ title: ""
description: ""
---

As of May 2023, the ElevenLabs has two models: `monolingual` and `multilingual`. The monolingual model is the first model released by ElevenLabs, which has only been trained on an English dataset. In contrast, the multilingual model has been trained on a dataset that includes a plethora of other languages, including French, German, Hindi, Italian, Polish, Portuguese, and Spanish.
As of May 2023, the ElevenLabs has two models: `monolingual` and `multilingual`. The monolingual model was the first model released by ElevenLabs; it was trained on an English dataset. In contrast, the multilingual model has been trained on a dataset that includes a plethora of other languages, including French, German, Hindi, Italian, Polish, Portuguese, and Spanish.

The v1 of the multilingual model is still in its experimental stage - there are still [bugs and refinements](/../troubleshooting) that need to be addressed. Nonetheless, for many tasks, it works perfectly well already. Keep in mind that introducing multiple languages also introduces more complexities and potential issues. One of the main things to be mindful of when using the multilingual model is to keep the generations short. Try and keep the text chunks below 800 characters if possible as some of the problems tend to get amplified the longer the generations are.

Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -14,4 +14,4 @@ Another important thing to keep in mind is that the AI will try to replicate the
- Root Mean Square (RMS) volume of the audio also plays a role in getting higher-quality clones.
- Feeding the AI audio that is very dynamic, meaning wide fluctuations in pitch and volume, will yield less predictable results.

If you are unsure about what is permissible from a legal standpoint, please consult the [Terms of Service](https://beta.elevenlabs.io/terms) for more information.
If you are unsure about what is permissible from a legal standpoint, please consult the [Terms of Service](https://beta.elevenlabs.io/safety) for more information.
5 changes: 3 additions & 2 deletions voicelab/overview.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@ description: ""

<iframe width="100%" height="400" src="https://www.youtube.com/embed/oD0ADULb_2w" title="YouTube video player" frameborder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share" allowfullscreen></iframe>

ElevenLabs offers high-quality [pre-made voices](/voicelab/pre-made-voices), our [Voice Design](/voicelab/voice-design) feature for custom creations, and a [cloning](/voicelab/voice-cloning) feature for replicating existing voices.
ElevenLabs offer high-quality [pre-made voices](/voicelab/pre-made-voices), a [Voice Design](/voicelab/voice-design) feature that allows you to create unique voices, and a [cloning](/voicelab/instant-voice-cloning) feature for replicating existing voices. When generating content on our paid plans, you get commercial rights to use that content. If you are on the free plan, you can use the content non-commercially with attribution. If you use a cloned voice, it is necessary to obtain the appropriate permission to use them commercially, even on a paid plan. Read more here.

The Voice Design feature allows users to select gender, age, and accent to generate unique voices. Keep in mind that it may take a few tries to find the perfect fit.

Expand All @@ -22,12 +22,13 @@ Although any voice can speak any language, it is important to note that the AI w
### Generated Voices (Voice Design)

- Custom voice creation with gender, age, and accent options
- Includes a row for different English accents to choose from
- Quality comparable to pre-made and cloned voices
- May require multiple attempts to find the desired voice

### Cloned Voices

- Better at replicating more common accents
- Cloning works the best for voices with more common accents
- Audio quality of samples is crucial for successful cloning
- Good audio length is about 1-2 minutes
- Consistent RMS volume may improve clone quality
Expand Down
2 changes: 1 addition & 1 deletion voicelab/pre-made-voices.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -3,5 +3,5 @@ title: "Pre-made Voices"
description: ""
---

ElevenLabs offers high-quality voices that are free to use, with the option for commercial use available on our paid tiers [(read more here)](https://help.elevenlabs.io/hc/en-us/articles/13313564601361-Can-I-publish-the-content-I-generate-on-the-platform-). There are both male and female voices to choose from, suitable for most use-cases. Although you can adjust the voice settings for some slight variations, if you require a more tailored voice, please continue reading.
There are both male and female voices to choose from, suitable for most use-cases. Although you can adjust the voice settings for some slight variations, if you require a more tailored voice, please continue reading.

2 changes: 1 addition & 1 deletion welcome/getting-started.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ We offer five public plans: `Free`, `Starter`, `Creator`, `Independent Publisher

Each plan details its offerings, including the character limits, the number of custom voices and cloned voices allowed simultaneously and the quality of audio provided. Please note that custom voices and cloned voices have different meanings.

It is important to note that cloning is only available on the `Starter` tier and above. The free plan offers three custom voices, but these are not the same as the custom-cloned voices. Instead, they are custom voices you can create without a voice designer tool.
It is important to note that cloning is only available on the `Starter` tier and above. The free plan offers three custom voices, but these are not the same as the custom-cloned voices. Instead, they are custom voices you can create with our Voice Design tool.

You can upgrade your subscription at any time, and the unused quota from your last subscription will roll over to the new plan. However, please remember that unused quota does not roll over from month to month; it is an allocated amount for that month only.

Expand Down

0 comments on commit 84e5b70

Please sign in to comment.