Voices from the ElevenLabs catalogue
Pick a voice from Deepnia’s ElevenLabs catalogue: search by name or style, then play its French or English preview before you generate.
Voice model · ElevenLabs
ElevenLabs — ElevenLabs voices, with the language and stability in your hands.
ElevenLabs is an AI audio company. On Deepnia, its model turns up to 5,000 characters into a voice-over with a voice from the ElevenLabs catalogue, in one of the 10 languages in the menu or with auto-detect. Three stability levels (Creative, Natural, Robust) set how expressive the voice is: it is the only Deepnia voice model with that setting.
- 5,000 characters
- Auto + 10 languages
- 3 stability levels
- ElevenLabs catalogue voices
- French or English previews
- WAV file
The voice generator opens with ElevenLabs already selected. The exact cost shows before every creation; you sign up when you generate.
- Creative
- Natural
- Robust
- Auto + 10 languages
At a glance
- Maker
- ElevenLabs
- Text
- Up to 5,000 characters per generation
- Languages
- Auto-detect + 10 languages
- Stability
- Creative, Natural, Robust
- Voices
- ElevenLabs catalogue, with previews
- Output
- 1 WAV file per generation
What ElevenLabs does best
Three stability levels
Under “Advanced settings”, choose Creative, Natural (the default) or Robust. According to ElevenLabs, lower stability widens the emotional range, while higher stability makes the voice steadier, for a long text with an even tone.
10 languages or auto-detect
Choose the language of your text: English, French, Spanish, German, Italian, Brazilian Portuguese, Japanese, Chinese, Korean, Hindi. Deepnia passes it to ElevenLabs; with auto-detect, the language is inferred from the text.
A WAV file ready for editing
Each generation delivers one WAV file (24 kHz, mono), an uncompressed format that drops easily into a video, a podcast or a presentation.
How to use ElevenLabs on Deepnia
Open the voice generator
The “Try ElevenLabs” button opens Deepnia’s voice generator with the model already selected.
Pick a voice
Search the ElevenLabs catalogue and play the French or English preview of a voice.
Write the text and set the language
Write up to 5,000 characters, then choose the language of the text or “Auto-detect”.
Set stability and generate
Under “Advanced settings”, choose Creative, Natural or Robust, check the cost shown, then click “Generate voice”.
ElevenLabs on Deepnia: what you can set
- Inputs
- Text
- Text
- 1 to 5,000 characters per generation
- Voices
- Deepnia’s ElevenLabs catalogue, with search and French or English previews
- Languages
- Auto-detect + 10 languages: English, French, Spanish, German, Italian, Brazilian Portuguese, Japanese, Chinese, Korean, Hindi
- Stability
- Creative, Natural (default), Robust
- Output
- 1 WAV file (24 kHz, mono) per generation
Prompt ideas to try
Copy a prompt, open the tool and adapt it to your project.
Ad voice-over for a coffee brand
- English
- Stability: Creative
- Warm male voice
Every morning starts with a promise: coffee roasted the day before, just for you. Meet Aurora, our new blend, in store today.
Online training module
- English
- Stability: Robust
- Calm female voice
Module two: simple bookkeeping for your business. First, we will sort your invoices; then we will track your expenses week by week.
Audiobook excerpt
- English
- Stability: Natural
- Deep narrator voice
That morning, the market woke long before sunrise. The stalls lit up one by one, and the smell of warm bread was already drifting up the street.
Fitness app onboarding in French
- Français
- Stability: Natural
- Energetic voice
Bienvenue dans votre nouveau programme d’entraînement. Indiquez votre objectif : nous préparons votre première semaine de séances en moins d’une minute.
Smartwatch launch in German
- Deutsch
- Stability: Creative
- Upbeat female voice
Heute stellen wir Ihnen unsere neue Smartwatch vor: leichter, schneller und mit einem Akku, der eine ganze Woche hält.
Wedding welcome message
- Auto-detect
- Stability: Natural
- Warm voice
Welcome, everyone, to this special day! Please take your seats; the ceremony begins in a few minutes. The couple thanks you for being here to share this moment.
Tips for better results
- Match stability to the job: Creative for a lively ad, Robust for a long training module with an even tone, Natural for everything else.
- For a short text, pick its language in the menu rather than auto-detect: a few words give little to go on.
- Play a voice’s French or English preview before you generate: timbre and accent matter as much as the script.
- Shape the rhythm with punctuation: ElevenLabs says ellipses add a pause.
- Write acronyms, dates and proper names the way they should be said, then listen to those passages again.
Good to know
- For a text longer than 5,000 characters, generate it in several parts cut at paragraph breaks, with the same voice and stability, then join the files in your editor.
- For a video series or training modules, keep the same voice, language and stability level: the sound stays consistent from one file to the next.
- For a narrated video, generate the voice-over first, then time the visuals to its rhythm in your editor.
ElevenLabs or another model?
Deepnia’s other voice and music models, to pick the right one for your project.
| Model | Inputs | Settings | Best for |
|---|---|---|---|
| ElevenLabsThis model | Text | Language, Stability, Expression tags | ElevenLabs voices, with the language and stability in your hands. |
| Open TTS | Text, Authorized personal voice | Language, Speed, Expression tags | 22 tags, adjustable speed, a personal voice and SRT captions. |
| Gemini Flash TTS | Text | Expression tags | A Google voice steered by tags, with the language detected automatically. |
| MiniMax Speech 2.6 HD | Text, Authorized personal voice | Language, Speed | A cloned voice, with adjustable speed and 23 languages + Auto. |
| Deepnia Long-form | Text, PDF, Authorized personal voice | — | A whole document, text or PDF, read into a single MP3 file. |
Frequently asked questions
Which languages can ElevenLabs speak on Deepnia?
The menu offers auto-detect plus 10 languages: English, French, Spanish, German, Italian, Brazilian Portuguese, Japanese, Chinese, Korean, Hindi. French is one of them, and ElevenLabs supports it on its multilingual models.
Which settings suit an ad, a training module or an audiobook?
For an ad, a warm or upbeat voice on Creative; for training, a calm voice on Robust; for an audiobook, a deep narrator voice on Natural. Play the previews to find the timbre that suits your audience.
What does the Stability setting do?
It sets how expressive the voice is, in three levels: Creative, Natural (the default) and Robust. According to ElevenLabs, lower stability widens the emotional range, while higher stability makes the voice steadier.
How do I prepare my script for a natural read?
Write acronyms, dates and proper names the way they should be said, and shape the rhythm with punctuation: ElevenLabs says ellipses add a pause. Then listen to the tricky passages again.
Can I listen to a voice before generating?
Yes: search the ElevenLabs catalogue by name or style, play a voice’s French or English preview, then generate your text with the voice you chose.
How much text can I convert at once?
Up to 5,000 characters per generation, delivered as one WAV file (24 kHz, mono). For a longer text, generate it in several parts and join them in your editor.
Can I make the same voice-over in several languages?
Yes: translate your script, then generate each version with its language picked in the menu, which offers 10 languages plus auto-detect.
ElevenLabs or Open TTS: which one should I use?
ElevenLabs for a voice from its catalogue and the stability setting. Open TTS to adjust the speed, use your own voice, direct the delivery with 22 tags or get SRT captions.
Ready to try ElevenLabs?
The voice generator opens with ElevenLabs already selected. The exact cost shows before every creation; you sign up when you generate.