French AI Voice

Siwis — free French text to speech

Siwis is a free female French AI voice — a Studio voice that runs on SpeakScribe's own servers, with adjustable speed. Type your text below to hear it read aloud, then download the audio. No account needed.

Female Studio voice Free

Make Siwis say your words

Voice details

Language
French
Gender
Female
Type
Studio · Kokoro
Download
WAV
Speed
Adjustable, 0.5×–2×
Voice ID
ff_siwis
Price
Free

How Siwis sounds — measured

Median pitch

205 Hz

In the middle of 7 female French voices

Intonation range

8.2 semitones

Close to typical for its group

Tone (spectral centroid)

2,126 Hz

Warmer, softer tone than most of its group

Speaking rate

17.9 characters/s

In the middle of 14 French voices on the same passage

Pitch across the sample passage dashed line = Siwis’s median

How long your audio will be at 17.9 characters/s

1,000 characters
≈ 56 s
5,000 characters (free limit per render)
≈ 5 min
  • ↔Compared with Denise, Siwis has a similar pitch (205 vs 197 Hz), livelier intonation (8.2 vs 4.7 semitones) and a warmer tone. Listen to Denise →
  • ↔Compared with Vivienne Multilingual, Siwis has a higher pitch (205 vs 159 Hz), livelier intonation (8.2 vs 5.0 semitones), a warmer tone and slower delivery (17.9 vs 20.8 characters/s). Listen to Vivienne Multilingual →

Measured by SpeakScribe, October 2026 · How we measure · Every French voice side by side

What Siwis fits best

  • Tutorials, kids' content and friendly explainers

    At 205 Hz it sits above 4 of the 7 female French voices, which sounds bright and approachable.

Use Siwis in a conversation

With Multi-voice, Siwis can read one character while Remy (a male French voice) reads another — the whole dialogue comes back as one MP3 with even volume between speakers. A free account can make 3 two-speaker dialogues a month; paid plans allow up to 4 speakers on Starter.

Try a dialogue with Siwis →

Formats, limits and help

Siwis: quick answers

Measured from its audio, Siwis has a median pitch 205 Hz (in the middle of 7 female French voices); intonation range 8.2 semitones (close to typical for its group); tone (spectral centroid) 2,126 Hz (warmer, softer tone than most of its group).
About 56 s. Siwis reads about 17.9 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 5 minutes of audio. Numbers, names and long pauses make it longer.