Arabic AI Voice
Sana — free Jordanian Arabic text to speech
Sana is a free female Jordanian Arabic AI voice — a Microsoft neural voice. Type your text below to hear it read aloud, then download the audio. No account needed.
Make Sana say your words
Sample: “مرحبًا، وأهلًا بك! هل تساءلت يومًا كيف سيبدو نصّك كتعليق صوتي حقيقي؟ يمكن لهذا الصوت أن يقرأ قصصك ودروسك ومقاطع منتجاتك، بهدوء ووضوح، أو بحماس وطاقة.”
Who is talking?
What do they say?
How to use Multi-voice
· Usually 5–20 seconds. Please keep this tab open and don't click again.
Subtitles preview · first 30 seconds
Next: YouTube title & tags from this text · transcribe a video
Voice details
- Language
- Arabic
- Accent
- Jordanian
- Gender
- Female
- Type
- Global · Microsoft neural
- Download
- MP3
- Speed
- Natural pace
- Voice ID
ar-JO-SanaNeural- Price
- Free
How Sana sounds — measured
Median pitch
204 Hz
The 2nd lowest of 16 female Arabic voices
Intonation range
11.4 semitones
Close to typical for its group
Tone (spectral centroid)
1,474 Hz
Balanced tone for its group
Speaking rate
8.4 characters/s
The slowest of 32 Arabic voices on the same passage
How long your audio will be at 8.4 characters/s
- 1,000 characters
- ≈ 1 min 59 s
- 5,000 characters (free limit per render)
- ≈ 10 min
- ↔Compared with Amany, Sana has a similar pitch (204 vs 205 Hz), livelier intonation (11.4 vs 5.4 semitones) and slower delivery (8.4 vs 11.1 characters/s). Listen to Amany →
- ↔Compared with Iman, Sana has a similar pitch (204 vs 206 Hz) and slower delivery (8.4 vs 9.3 characters/s). Listen to Iman →
Measured by SpeakScribe, October 2026 · How we measure · Every Arabic voice side by side
What Sana fits best
Documentaries and serious explainers
At 204 Hz it sits below 14 of the 16 female Arabic voices, which gives a calm, authoritative sound.
Lessons and step-by-step guides
At 8.4 characters a second it is one of the slower Arabic readers — easy to follow.
Use Sana in a conversation
With Multi-voice, Sana can read one character while Shakir (a male Arabic 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.