AO3 to MP3: One Link, a Different Voice for Every Character
AO3 to MP3: paste a chapter link and download an MP3 with a different voice for each character. Free to try with no card, plus whole-fic import.
Posted by
Claude Opus 5.5Related reading
AO3 Text to Speech: Free Read Aloud or a Voice for Each Character
Does AO3 have text to speech? No. Make AO3 read aloud free on iPhone, Android or PC, or hear each character in a different voice with LyricWinter.
Text to Speech for Writers: Hear Your Chapter Before You Post
Text to speech for writers: LyricWinter gives every character a voice, so a line in the wrong voice points to a weak dialogue tag. The test is free.
Best AI Audiobook Generator in 2026: A Voice for Every Character
Our pick for the best AI audiobook generator with multiple voices: LyricWinter gives each character its own AI voice. Hear samples and see chapter costs.
Quick answer
To turn an AO3 fic into an MP3, open a new project in LyricWinter Studio and import the chapter link (Import, then AO3 chapter). Press Create audio, then Export final mix to download one MP3. Each character gets their own voice, and a narrator reads the rest. For a long fic, choose AO3 work to import up to 500 chapters with one cast. It's free to try, with no card needed.
Your phone's read-aloud gives every character the same voice. When two characters are both "she," you lose track of who said what, and in the car you can't look back at the page to check. LyricWinter Studio gives each character their own voice and lets a narrator read the rest. Then you download the chapter as an MP3 and play it offline in the car, at the gym, or in bed.
Press play below to hear it, then try it free with a short chapter.
Hear the difference: two women, both "she," two voices
This short scene was written for this blog. LyricWinter Studio did the rest: it found the four speakers, gave each one an AI voice, and made the audio. Listen to the end, where two women share "she" for several lines. That's where read-aloud loses you. Here, every one of those lines went to the right speaker, including "It might.", which has no "she said" to show who is talking.
Made in LyricWinter Studio
Fog on the Marigold: full cast
Voices: Narrator, Mireille, Captain Ines Varga, Pell
Read the transcript: Fog on the Marigold
Speakers: Narrator, Mireille, Captain Ines Varga, and Pell. Original scene written for the LyricWinter blog.
The storm hit the Marigold an hour past midnight, and by then the mage had been aboard for three days, which was exactly three days too long.
“You told me this crossing was calm,” Mireille said, gripping the chart table as the deck tilted under them.
“I told you it was fast,” Captain Ines Varga said. “Calm costs extra.”
“I paid extra!”
“You paid for silence. Different line item.”
Pell stuck his head down the hatch, soaked to the skin. “Captain, we’ve lost the lantern on the foremast, and the lookout says there are lights off the port side. Customs cutter. Maybe two.”
Ines swore under her breath. “How far?”
“Close enough that they’ll hear you swearing.”
Mireille let go of the table. “Then let me do something about it.”
“Absolutely not. Last time you did something about it, my ship smelled like burnt sugar for a week.”
“It worked, didn’t it?”
She didn’t answer, which was an answer.
* * *
Ten minutes later the Marigold was wrapped in fog. The cutter’s lights slid past close enough to touch, then drifted away toward Ceirnach Sound.
Ines leaned on the rail beside the mage. Her hands were shaking. “That was reckless,” she said.
“That was brilliant,” Mireille said. “You can say brilliant. It won’t kill you.”
“It might.”
Mireille laughed, low and tired, and bumped her shoulder against the captain’s. Ines didn’t move away.
“Don’t tell the crew,” Ines whispered.
“Tell them what?”
“That I said thank you.”
“You didn’t say thank you.”
“I’m saying it now.” She said it so quietly that the fog almost took it. “Thank you.”
If a line lands on the wrong speaker in your chapter, you can fix it before you make the audio.
Before you start
- It's free to try. The free plan makes about 17 minutes of audio a month, enough for one short chapter. No card needed.
- For a long car trip, you need more minutes. MyWinter ($6 a month) makes about 1 hour 40 minutes of audio a month. UltraWinter ($20 a month) makes about 8 hours, enough for a 4-hour drive there and back. Words you pay for never expire.
- You sign in with Google or Apple. Once the MP3 is downloaded, it plays anywhere without an account.
- Every voice is an AI voice. Studio is in beta, which means it's still being tested and improved. The sample above is what it sounds like, so let your ears decide.
The minutes above are for most voice engines (the AI models that speak the lines). ElevenLabs v4, the one Studio picks whenever a voice works with it, costs more: a few extra words per line for acting notes now, and three times as many words from October 12, 2026. Check the cast first, which is free, and the Create audio button shows the full cost before you spend anything.
How to convert an AO3 chapter to MP3 in four steps
These steps work in your phone's or computer's browser and were checked on October 1, 2026. There's nothing to install.
- Copy the chapter link. On AO3, open the chapter and copy its link from the address bar. It looks like
archiveofourown.org/works/12345/chapters/67890. Read the author's notes while you're there, because the import leaves them out. - Import it into a new project. Open the New project window in LyricWinter Studio. The first time, Studio asks you to sign in with Google or Apple. After that, come back and tap the link again. Open the Import menu, choose AO3 chapter, paste the link, and press Review. The review screen shows the chapter's word count, so you can see whether it fits your free words. Press Import.
- Make the audio. Press Create audio. Studio finds the characters, gives each one a voice, and makes the audio. The number on the button shows about how many words it will use. You can start listening before the chapter is done.
- Download the MP3. When the audio is done, open the ⋯ menu on the player bar at the bottom and choose Export final mix. Keep MP3, press Create MP3 export, then Download MP3. It saves like any other download, usually in your Downloads folder (on iPhone, in the Files app).
Optional: check the cast first (free)
You can skip this, but it shows the full cost before you spend anything. Before step 3, press Manual voice assignment next to Create audio (on a phone, it's in the arrow menu next to Create audio). Studio finds the characters and suggests a voice for each, for free. Then the number on Create audio includes any extra words for ElevenLabs v4 or Auto emotion.
To swap a voice or a character's engine, open the ⋯ menu at the top and choose Characters & voices. To fix a line with the wrong speaker, tap the people icon with a number at the top, open Lines, tap the line's speaker name, pick the right Speaker, and press Save speaker & block.
On the free plan, one chapter can be up to 30,000 text characters, about 5,300 words. If yours is longer, the Section limit reached window offers Trim the end to fit… on any plan and Divide into sections on paid plans.
Long fic? Import every chapter at once and keep one cast
Choose AO3 work instead of AO3 chapter and paste the work link once. Studio imports up to 500 chapters as one project, with one section per chapter in the author's order. Characters belong to the whole project, so the voice a character has in chapter 1 is still theirs in chapter 40.
- Open the New project window, open the Import menu, and choose AO3 work. Paste the work link and press Review. Already downloaded the fic as an EPUB (an ebook file) from AO3's Download menu? Choose EPUB file instead (up to 20 MB). An EPUB keeps everything in the file, including the author's notes. Use the EPUB of a locked work only if the author is fine with it.
- The review screen lists each chapter with its length. Untick anything you don't want (or use All and None) and press Import. Nothing is created until you confirm.
- Follow steps 3 and 4 above for each chapter. Open the next chapter from Projects & Sections. Returning characters already have their voices.
Each chapter becomes its own MP3, named after its section, like tracks on an album. If your player mixes up the order, add chapter numbers to the names. Exports don't last forever, so download each one when it's ready. If an export shows as expired, create it again.
To keep a character's voice in future projects too, open the character and press Pin as default. The next time that name shows up, the same voice and engine come back. Our voice pinning guide has the details.
When the author posts a new chapter, add it to the same project so the cast stays the same. Tap + at the top (New section). Open the ⋯ menu in the top toolbar, choose Import story, then From link, and paste the chapter link. Keep Current chapter, press Review import, and choose Import as one section.
Import your whole fic into Studio
Free to import and cast. You only spend words on audio.
For the bigger picture, our fanfiction reader page covers how to turn AO3 into an audiobook.
How much does it cost to turn an AO3 chapter into an MP3?
You pay in LyricWinter words instead of minutes, because Studio counts the words of the story it reads. You spend them only on audio. Finding the characters, designing new voices, and AI sound effects are free. Every voice engine except ElevenLabs v4 is 1×, which means one word of story uses about one LyricWinter word, so 2,500 words make about 17 minutes of audio.
As of October 1, 2026, here's how much listening each plan makes on 1× engines, and what a 4,000-word chapter (about 27 minutes of audio) costs. Yearly plans give you the whole year's words at the start. Word packs are words you buy once, only when you need them.
| Plan | Price | Words and listening time | A 4,000-word chapter |
|---|---|---|---|
| Free | $0 | 2,500 words a month, about 17 minutes | Fits a chapter up to about 2,500 words each month |
| MyWinter | $6 a month | 15,000 words a month, about 1 hour 40 minutes | about $1.60 |
| MyWinter yearly | $59.99 a year | 180,000 words at the start, about 20 hours | about $1.33 |
| UltraWinter | $20 a month | 72,500 words a month, about 8 hours | about $1.10 |
| UltraWinter yearly | $199.99 a year | 870,000 words at the start, about 98 hours | about $0.92 |
| Word packs | Buy when you need them | 2,500 words per dollar, about 17 minutes | about $1.60 |
A 4-hour drive is about 35,000 words of story: about $14 at MyWinter or word-pack rates, or about $8 at the yearly UltraWinter rate. See pricing for current plans.
Paid words never expire, so words you don't use this month carry over. Studio charges only for lines that finish, and redoing a line with New take uses words again. Section limits differ by plan: 30,000 text characters on the free plan, 90,000 on MyWinter, and 150,000 on UltraWinter.
ElevenLabs v4 and October 12
ElevenLabs v4 is the engine Studio picks for new casts whenever a voice works with it. Until October 12, 2026, it's 1× like the others. From then on, it uses three times as many words. In the US, that starts on the evening of October 11: 5 p.m. in California and 8 p.m. in New York (midnight UTC, the world's standard clock).
After that, a 4,000-word chapter with every voice on v4 uses about 12,000 words, about $2.76 to $4.80. When your cast uses v4, the Audio options menu next to Create audio shows a note about the change.
Mix engines to spend less
Every character has its own engine menu in Characters & voices. So you can keep the main characters on ElevenLabs v4 and move the narrator to a 1× engine such as Inworld TTS 2, another AI voice engine. In chapters with lots of narration, the narrator reads most of the words, so that one change saves the most.
Say a 4,000-word chapter has 2,800 words of narration and 1,200 words of dialogue. After October 12, that mixed cast uses about 6,400 words instead of 12,000. On MyWinter, that's about $2.56 instead of $4.80. Here's a mixed cast: Tamsin and Dario run on ElevenLabs v4, and the narrator and Bev run on Inworld TTS 2.
Made in LyricWinter Studio
Floor Nineteen: mixed engines
Voices: Narrator, Tamsin, Dario, Bev
Read the transcript: Floor Nineteen
Speakers: Narrator, Tamsin, Dario, and Bev on the elevator intercom. Original scene written for the LyricWinter blog.
The elevator gave one polite chime, shuddered, and stopped somewhere between the eighteenth and nineteenth floors.
Tamsin stared at the dark panel. “No. Absolutely not. Not tonight.”
“It’s fine,” Dario said, already jabbing the button with the little bell on it. “These things reset. Give it a second.”
“You said that about your car. Twice.”
The speaker above the door crackled. “Front desk, this is Bev. Are you folks stuck, or just enjoying the privacy?”
“Stuck,” they both said.
“Oh, wonderful,” Bev said, and she sounded like she meant it. “Engineer’s on his way. Twenty minutes, maybe forty. Anybody hurt? Pregnant? Claustrophobic?”
Tamsin pressed her back against the mirrored wall. “Does being trapped with my ex-boyfriend count as a medical condition?”
There was a long pause. “Honey, I’m going to put that down as a yes.”
Dario laughed, the real laugh, the one she used to wait for. Then he stopped. “You gave a good toast tonight.”
“Don’t.”
“I mean it. The part about Priya learning to ride a bike at twenty-six...” He shook his head. “Half the room was crying.”
“I was crying,” Tamsin said quietly. “I just did it in the bathroom, like a professional.”
He looked at the floor. “I should have called you. After I left for Lisbon. I kept writing texts and deleting them.”
“Eleven months, Dario.”
“I know.”
“Eleven months, and the first thing you say to me is ‘nice toast’?”
“It was a very nice toast!”
The speaker crackled again. “Sorry to interrupt, you two. The engineer wants to know if you’ve tried turning it off and on again.”
Tamsin covered her face and laughed until it turned into something closer to a sob. Dario reached over, slowly, and took her hand. She let him.
“Bev,” she whispered. “Tell him to take his time.”
Auto emotion is a setting that's on by default. It writes short acting notes that tell each voice how to say a line, for lines that don't have any yet. On ElevenLabs v4 lines, those notes use a few extra words: Studio estimates about 14 per line now, and about 40 from October 12. You pay only for the notes Studio actually sends. To turn Auto emotion off, open Audio options, the arrow next to Create audio. For more on v4, read the ElevenLabs v4 audio tags guide.
Can you make an MP3 of someone else's AO3 fic?
This guide is about making an MP3 to listen to on your own. For someone else's fic, keep it that way, and ask the author first if you ever want to post or share the audio.
- Read the author's notes on AO3. The import leaves them out, and that's where authors put context and thanks.
- Respect locked works. Works that AO3 shows only to logged-in users can't be imported. Paste one only if the author's notes or profile say they're fine with it.
- Keep it private. A podfic is a fan-made audio version of a fic. AO3's Terms of Service FAQ says a podfic of someone else's work can be posted on AO3 only with the creator's permission.[1] Studio shares nothing until you create a listening link, so keep that step for your own work or work whose author said yes.
- Leave kudos and comments on AO3. That's how an author knows someone enjoyed the work.
For podfic and every other way to listen, see how to listen to fanfiction. Writing your own fic? Hear your chapter before you post it.
AO3 to MP3 errors and how to fix them
| Message you see | What to do |
|---|---|
| “Paste an Archive of Our Own work or chapter link.” | Copy the whole AO3 link, starting with https://. For FanFiction.net, SpaceBattles, or Substack, use Import story in a section instead. |
| “That AO3 link is not a specific work or chapter. Open the work on AO3 and paste its /works/… link.” | Series, tag, and profile pages don't import. Open the work or chapter and copy that link. |
| “This story requires an AO3 account. Copy and paste it into Studio instead.” | The work is locked to AO3 users. Paste it only if the author's notes or profile say they're fine with it. |
| “AO3 took too long to return the full work. Try importing the current chapter instead, or paste the text directly.” | Import one chapter at a time with AO3 chapter, or try again later. |
| “AO3 could not find that public story. Check the link, or paste the text directly.” | Check the link. The work may have been deleted or locked. |
| “Too many story import requests. Please try again later.” | You can try up to 10 imports an hour, and failed tries count. Wait, then try again. |
| “Section limit reached” | The chapter is longer than your plan allows for one section (30,000 text characters on the free plan). Choose Divide into sections on a paid plan, Trim the end to fit…, or upgrade. |
| “Need more words” | Move some characters to a 1× engine, pick a shorter chapter, or add words with a plan or a word pack. |
AO3 to MP3: FAQ
Can I turn a whole AO3 fic into one MP3?
You get one MP3 per chapter. LyricWinter Studio imports up to 500 chapters of an AO3 work, from the work link or an EPUB ebook file, as one project with one cast. It exports each chapter as an MP3 named after its section title. If your player puts the files out of order, add chapter numbers to the names.
How much does one chapter cost?
You pay in LyricWinter words, counted from the story text and used up as audio is made. Every voice engine except ElevenLabs v4 is 1×: about one LyricWinter word per word of story. As of October 1, 2026, a 4,000-word chapter (about 27 minutes of audio) on 1× engines costs about $1.60 on MyWinter or a word pack, about $1.10 on monthly UltraWinter, and about $0.92 on yearly UltraWinter. ElevenLabs v4 is 1× until October 12, 2026 (UTC), and uses three times as many words after that.
Is there a free AO3 to MP3 converter?
Yes. LyricWinter's free plan makes 2,500 words of audio a month, about 17 minutes on 1× engines, with a different voice for each character, and it needs no card. You download the result as an MP3. Finding the characters is free. On the free plan, one section can hold up to 30,000 text characters, about 5,300 words. From October 12, 2026 (UTC), the ElevenLabs v4 engine uses three times as many words, so the same month covers about 830 words of story on v4. Redoing a line uses words again.
Do I need an account?
Yes. LyricWinter Studio asks you to sign in with a Google or Apple account, and the free plan needs no card. Once the MP3 is downloaded, it plays on any device without an account.
Will my characters keep the same voices in every chapter?
Yes. In a LyricWinter Studio project, characters belong to the whole project, so each one keeps the same voice and engine in every chapter. To carry a voice into other projects, open a character and press Pin as default. That voice comes back the next time the name appears.
Can I listen to an AO3 fic offline?
Yes. Download the MP3, which your browser saves like any other download. Then play it in any music or files app with no internet. If you only want the text offline, AO3's Download button saves a work as an EPUB ebook, a PDF, and other formats.
Does the MP3 include the author's notes?
Not with an AO3 link import. It keeps only the story text and removes the summary, the author's notes, and the work header, so read them on AO3 before you listen. An EPUB imported into Studio keeps everything in the file, notes included.
Can I post or sell the audio I make?
You own the audio you make, so you can use it however you like, as long as you're allowed to use the voices and the text. LyricWinter's Terms of Service, the site's rules, allow any legal use, including posting or selling it. The one exception is audio made with the F5-TTS engine, which is for personal use only, not for making money. For someone else's fic, ask the author first. AO3's Terms of Service FAQ says a podfic (a fan-made audio version) of someone else's work can be posted on AO3 only with permission.
Is my audio private?
Yes, by default. LyricWinter Studio shares nothing until you create a listening link, and Stop sharing turns the link off. Keep audio of other people's fics for yourself.
Does it work on iPhone and Android?
Yes. Open lyricwinter.com/studio in your phone's browser and follow the same steps. There's nothing to install.
Can I import from FanFiction.net, SpaceBattles, or Substack?
Yes. Open a section, then open the ⋯ menu in the top toolbar, choose Import story, then From link. A FanFiction.net link imports one chapter. A SpaceBattles thread link imports one page of the thread's reader view. A public Substack post link imports that post. Links from Wattpad, Royal Road, and other story sites don't import, so paste the chapter text instead.
Can I import a locked AO3 work?
No. The import can only read works that AO3 shows to everyone. If a work is locked, check the author's notes or profile first, and paste the text only if they say they're fine with it.
Can I share the audio of my own fic?
Yes. In LyricWinter Studio, open the ⋯ menu on the player bar at the bottom, choose Share listening link, then Create listening link. Listeners get the audio with the text to read along, the link stays current as you edit, and Stop sharing turns it off.