English AI Voice

River — free American English text to speech

River is a free female American English 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 American accent Studio voice Free

Make River say your words

Voice details

Language
English
Accent
American
Gender
Female
Type
Studio · Kokoro
Download
WAV
Speed
Adjustable, 0.5×–2×
Voice ID
af_river
Price
Free

How River sounds — measured

Median pitch

166 Hz

The 6th lowest of 19 female American English voices

Intonation range

5.6 semitones

Steadier than typical for female American English voices (8.9)

Tone (spectral centroid)

1,974 Hz

Balanced tone for its group

Speaking rate

228 words/min

The 2nd fastest of 75 English voices measured

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

How long your audio will be at 20.6 characters/s

1,000 characters
≈ 48 s
5,000 characters (free limit per render)
≈ 4 min
  • ↔Compared with Emma, River has a similar pitch (166 vs 168 Hz), steadier intonation (5.6 vs 13.8 semitones), a brighter tone and faster delivery (228 vs 193 words/min). Listen to Emma →
  • ↔Compared with Emma Multilingual, River has a similar pitch (166 vs 173 Hz), steadier intonation (5.6 vs 12.6 semitones) and faster delivery (228 vs 184 words/min). Listen to Emma Multilingual →

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

About the River voice

River is a female American English Studio voice with a mid-range pitch (166 Hz) and the fastest default pace of the American female Studio voices: 228 words per minute on our test passage. That energy fits short-form video, quick explainers and list-style content.

Tips for natural results with River

  • For long narration, slow River to about 0.85×; for Shorts and Reels, 1.0× already sounds snappy.
  • Shorter sentences keep a fast voice easy to follow — break long sentences in two.
  • If River feels too quick even when slowed down, Bella (182 wpm) and Sarah (191 wpm) are naturally calmer.

Use River in a conversation

With Multi-voice, River can read one character while Adam (a male English 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 River →

Formats, limits and help

River: quick answers

Measured from its audio, River has a median pitch 166 Hz (the 6th lowest of 19 female American English voices); intonation range 5.6 semitones (steadier than typical for female American English voices (8.9)); tone (spectral centroid) 1,974 Hz (balanced tone for its group).
About 48 s. River reads about 20.6 characters a second, spaces included (measured on its sample passage), so the free limit of 5,000 characters per render is about 4 minutes of audio. Numbers, names and long pauses make it longer.