Narration studio

Text to speech with voices you choose — or make

Paste a script, pick a voice and generate narration. The same picker holds stock voices from four providers and the voices you cloned or designed, so your channel can sound like you.

97 credits short

🔊 You are using standard Text-to-Speech.Free users have daily character limits and limited premium voices. Upgrade for premium voices, longer text, and better stability.
97/2,000 characters
Login for higher limits

Pick language, voice, and generate audio.

No voices found for "ALL"
Voice Settings

Three kinds of voices in one picker

Made for scripts, not single sentences

  • Multi-segment mode: split a script into segments and get one audio file per segment, ready to drop onto a timeline.
  • Preview a short excerpt before spending credits on the whole script.
  • Pitch, speed and volume controls, plus speaking styles on voices that support them.
  • Gemini emotion tags such as [excited] or [happy] at the start of a line to steer delivery.
  • Language detection that switches the voice list to match your text.
  • A history of recent generations and a share link for each result.

Tips for natural-sounding narration

  • Write the way you speak. Short sentences and real punctuation give the voice room to breathe.
  • Remove stray line breaks copied from PDFs; they create unnatural pauses.
  • Spell out numbers, units and abbreviations the way they should be read aloud.
  • Preview the hardest paragraph first — names and technical terms — before generating everything.

Need more than one voice or a subtitle file?

Frequently Asked Questions

Q: How long can a script be?

A: Each generation has a character limit that depends on your plan; the counter under the text box shows it. Longer scripts can be split with multi-segment mode.

Q: Can I use my cloned or designed voice here?

A: Yes. Open the voice picker and switch to “My voices”. Custom voices need a Basic plan or higher.

Q: Why do some voices cost more credits?

A: Each voice has a credit rate per character, shown next to it in the picker. Gemini, OpenAI and Chirp voices use more credits than standard neural voices.

Q: Can I control emotion?

A: Voices with speaking styles let you pick one, and Gemini voices respond to emotion tags like [excited] at the start of a line.

Q: What format is the audio?

A: Results play in the browser and download as MP3.

Just want a quick, free read-aloud without custom voices? TTSForFree is a simpler free tool built on the same voice technology.