Translate audio from Spanish to English
Upload a Spanish recording, check every English line next to the original, and download English speech timed to it, with the English script as a subtitle file.
MP3, M4A, WAV and other audio up to 100 MB and 5 minutes.
Sign in to dub into up to 5 languages in one run. Sign in free
Voice sample
Keep parts in the original language (optional)
One time range per line, like 1:05-1:20. Lines that start inside a range are not translated, voiced or counted, and those parts keep the original sound. You can also keep single lines after translation.
Glossary and style (optional)
One term per line. Write a name to keep it as is, or "source = translation" to fix how it is translated. Start a line with a language tag, like "[fr] mic = micro" or "[es-419] bus = camión", to use it for that language only.
CSV: the term in the first column and its translation in the second. Leave the second column empty to keep the term as is.
Tone, formality or audience in a few words, up to 300 characters. They shape the wording only; they cannot change the rules, the language or your limits.
Names, brands and acronyms said in the recording, separated by commas (up to 100). They help the speech recognizer spell them right. They do not change the translation; use the glossary for that.
Uploaded and processed audio is stored on SoundHalo. Audio access expires after 30 days (longer on paid plans, up to a year); expiry does not confirm storage deletion. Delete the stored files here before leaving this page. Speech providers have their own retention policies. Privacy policy.
Example: a Spanish cooking lesson in English
A 19-second Spanish cooking lesson with quiet background music, dubbed into English with the Heart voice and mixed over the lowered original. All four English lines fit their time without speeding up. Nothing was edited.
| Time | Spanish | English dub |
|---|---|---|
0:00.8 → 0:04.7 | Hola y bienvenidos a la lección tres. | Hello and welcome to lesson three. |
0:04.7 → 0:09.2 | Hoy vamos a preparar una receta muy sencilla. | Today we'll make a very simple recipe. |
0:09.2 → 0:14.2 | Primero, corta dos tomates en trozos pequeños. | First, cut two tomatoes into small pieces. |
0:14.2 → 0:19.0 | Después, añade aceite de oliva y una pizca de sal. | Then add olive oil and a pinch of salt. |
Original Spanish recording
English dub over the lowered original
How to translate a Spanish recording into English
- Upload the recording. English is already selected as the dub language.
- Pick one of 20 US English or 8 British English voices.
- Transcribe and translate. Each English line appears next to the Spanish it replaces, with its time.
- Fix any line, translate one line again, or clear it to skip it. Nothing is voiced until you choose Create dubbed audio.
- Choose the mix, create the dub, listen on the page, and download the MP3 or WAV with the English SRT.
English speech, English text, or both
- The dub is English speech timed to the Spanish, for listeners who would rather hear the recording than read it.
- The SRT file is the English script with a time for every line, so you can read the translation, quote it or use it as subtitles.
- For the Spanish words only, with no translation, MP3 to text writes a transcript.
In our tests, English ran shorter than Spanish
In our two Spanish test clips, the English translation was 17% shorter than the Spanish (320 characters became 267), and all 7 English lines fit their time without speeding up. Each English line starts when the Spanish line started and may use up to 2 seconds of the pause after it. A line that runs long is sped up to at most 1.25 times without changing the pitch, and the line check marks any line that still runs over.
Background music and the Spanish voice
- Dub over the original music and sound: a speech separation model removes the Spanish voice and keeps the music, for recordings up to 10 minutes.
- Dub over the lowered original: the whole recording drops by about 15 dB while the English speaks, so the Spanish voice stays faintly audible.
- Voice only: a track with just the English voice, timed to the original, to place over your own music. If the last line runs long, the track can end a little after the original.
Limits
- No account: recordings up to 5 minutes, and a dub preview of up to 300 speech characters (about 20 seconds of speech) and 20 lines. Longer scripts dub the first lines that fit. Speech characters (1,200 a day), translations (5 a day) and transcription minutes are shared by everyone on your network and capped by a site-wide free budget, so they can run out.
- Free account: recordings up to 30 minutes, up to 3,000 speech characters (about 3 minutes of speech) and 200 lines per dub, 20,000 characters a day.
- Pro: recordings up to 30 minutes, up to 20,000 speech characters (about 20 minutes of speech) and 500 lines per dub, 300,000 characters a day.
- Speech characters are shared with the text to speech and voice-over tools. Voices from Giggy count each line as whole blocks of 20 characters. Mixing the dub over the original counts the recording length once toward the daily cloud processing allowance; keeping the music and background sound counts it twice (removing the speech, then the mix), or three times when parts keep the original language. Limits reset at midnight UTC.
Synthetic voice and acceptable use
The English dub is read by a text to speech voice, not by the original speaker. Translate recordings you made or have the rights to translate, such as your own podcast, course or voice notes. Do not use it to make someone appear to say something they did not. Tell listeners the English audio is AI generated; some platforms require that label.
Related tools
FAQ
Can I get the English as text instead of speech? +
Yes. Every dub comes with the English script as an SRT file: plain text with a start and end time for each line, which any text editor opens. If you only need the Spanish words written down, use MP3 to text instead; nothing is translated or voiced.
Which Spanish accents does it understand? +
Spanish from Spain, Mexico, Argentina, Colombia or anywhere else. Lemonfox transcribes the recording with Whisper large-v3 (another provider takes over if Lemonfox fails) and detects the language on its own. You can correct any line before the English voice is made.
Can I choose American or British English? +
Yes. There are 20 US English voices and 8 British English voices, male and female, each with a sample to play first.
Which audio files work? +
MP3, M4A, WAV, OGG, FLAC and most other audio files, including WhatsApp voice notes and phone recordings. For a video file, use the Spanish to English video page, which returns an MP4.
Will the English voice sound like the speaker? +
By default the dub uses a stock synthetic voice you pick. Signed in, you can choose original speakers' voices: each person is cloned from a few seconds of their own Spanish speech and speaks the English lines, charged at the voice provider's real cost and only after you confirm you may dub them. Anyone without enough clear speech for their own voice reference is voiced with another speaker's cloned voice.
Where is my recording processed? +
The recording is uploaded to SoundHalo. Lemonfox transcribes the Spanish, the DeepSeek model translates it through OpenRouter (only hosts that OpenRouter lists as not collecting user data), and Lemonfox reads the English lines. Speech separation sends only the audio track to a GPU server SoundHalo rents from Modal, where it is deleted when the request finishes; mixing runs on SoundHalo's own servers. Access to the files expires after 30 days (longer on paid plans), and you can delete them from the page.
What are the limits? +
No account: recordings up to 5 minutes, and a dub preview of up to 300 speech characters (about 20 seconds of speech) and 20 lines. Longer scripts dub the first lines that fit. Speech characters (1,200 a day), translations (5 a day) and transcription minutes are shared by everyone on your network and capped by a site-wide free budget, so they can run out. Free account: recordings up to 30 minutes, up to 3,000 speech characters (about 3 minutes of speech) and 200 lines per dub, 20,000 characters a day. Pro: recordings up to 30 minutes, up to 20,000 speech characters (about 20 minutes of speech) and 500 lines per dub, 300,000 characters a day. Speech characters are shared with the text to speech and voice-over tools. Voices from Giggy count each line as whole blocks of 20 characters. Mixing the dub over the original counts the recording length once toward the daily cloud processing allowance; keeping the music and background sound counts it twice (removing the speech, then the mix), or three times when parts keep the original language. Limits reset at midnight UTC.