Pricing

from $9.00 / 1,000 1,000 characters converteds

Try for free

Go to Apify Store

Bulk Text to Speech: MP3 + SRT Subtitles | No API Key

Try for free

Convert texts or an Excel/CSV file into MP3 voiceovers with perfectly timed SRT/VTT subtitles. 322 neural voices in 75 languages, word-by-word TikTok captions, personalized messages from spreadsheet rows, and one merged file option. No API key needed.

Pricing

from $9.00 / 1,000 1,000 characters converteds

Rating

0.0

(0)

Developer

youssef farhan

Actor stats

Bookmarked

Total users

Monthly active users

4 hours ago

Last modified

Categories

Automation

MCP servers

Integrations

Texts to convert

texts

Optional

One entry = one MP3 voiceover (plus matching subtitles). Add as many as you want: they are all generated in parallel. With a spreadsheet attached, write a text with column names in double curly braces, for example: Hi {{First name}}, your order {{Order}} has shipped. It is filled in for every row. Texts without placeholders are ignored in that case.

Type:array

Spreadsheet (optional)

spreadsheetFile

Optional

Optional. Upload an Excel (.xlsx), CSV or TSV file, or paste a public link to one (Google Sheets links work if the sheet is shared as 'Anyone with the link'). The first row must be the column names. Each row becomes one voiceover: either from a text above with {{Column}} placeholders, or from the text column below. You get your file back as results.xlsx with the MP3 and subtitle links on every row. Leave empty to use the Texts list as usual.

Type:string

Text column (spreadsheet only)

textColumn

Optional

Which column holds the text to read aloud, when you do not write a {{Column}} template above. Leave empty to pick it automatically: a column named 'text' or 'script' if there is one, otherwise the column with the longest text.

Type:string

File name column (spreadsheet only)

fileNameColumn

Optional

Optional. A column whose value is added to each file name, for example a SKU or a lesson name: audio-001-SKU-123.mp3 instead of audio-001.mp3. Leave empty for numbered names.

Type:string

Sheet name (optional)

sheetName

Optional

Only for Excel files with several sheets. Leave empty to read the first sheet.

Type:string

Voice

voice

Optional

Neural voice used for all texts. 322 voices in 75+ languages are available — this list shows the most popular ones. Need another? Use the 'Custom voice code' field below, or tick 'List all voices' to export the full catalog.

Type:string

Default:en-US-AriaNeural

Options:

en-US-AriaNeuralen-US-JennyNeuralen-US-MichelleNeuralen-US-AnaNeuralen-US-GuyNeuralen-US-ChristopherNeuralen-US-EricNeuralen-US-AvaMultilingualNeuralen-US-EmmaMultilingualNeuralen-US-AndrewMultilingualNeuralen-US-BrianMultilingualNeuralen-GB-SoniaNeuralen-GB-RyanNeuralen-AU-NatashaNeuralen-IN-NeerjaNeurales-ES-ElviraNeurales-MX-DaliaNeurales-MX-JorgeNeuralfr-FR-DeniseNeuralfr-FR-HenriNeuralde-DE-KatjaNeuralde-DE-ConradNeuralit-IT-ElsaNeuralit-IT-DiegoNeuralpt-BR-FranciscaNeuralpt-BR-AntonioNeuralar-SA-ZariyahNeuralar-EG-SalmaNeuralhi-IN-SwaraNeuralja-JP-NanamiNeuralko-KR-SunHiNeuralzh-CN-XiaoxiaoNeuralzh-CN-YunxiNeuralru-RU-SvetlanaNeuraltr-TR-EmelNeuralnl-NL-ColetteNeuralpl-PL-ZofiaNeuralsv-SE-SofieNeuralid-ID-GadisNeuralvi-VN-HoaiMyNeuralth-TH-PremwadeeNeural

Speaking speed

speed

Optional

How fast the voice talks. TikTok/Shorts creators often use +25%.

Type:string

Default:+0%

Options:

-50%-25%-10%+0%+10%+25%+50%+100%

Pitch

pitch

Optional

Voice pitch adjustment.

Type:string

Default:+0Hz

Options:

-20Hz-10Hz+0Hz+10Hz+20Hz

Custom voice code (optional)

customVoice

Optional

Any of the 322 supported voice codes, e.g. el-GR-AthinaNeural. Overrides the Voice dropdown. Tick 'List all voices' below and run once to export the full catalog.

Type:string | null

Generate subtitles

generateSubtitles

Optional

Create a perfectly timed subtitle file (SRT or VTT) next to every MP3 — ready to drop into CapCut, Premiere, DaVinci or YouTube.

Type:boolean

Default:true

Subtitle timing

subtitleGranularity

Optional

'Word-by-word' gives you one cue per word — perfect for animated TikTok-style captions. 'Sentence' gives classic subtitle blocks.

Type:string

Default:sentence

Options:

sentenceword

Subtitle format

subtitleFormat

Optional

SRT works everywhere (CapCut, Premiere, YouTube). VTT is for web players.

Type:string

Default:srt

Options:

srtvtt

Also merge everything into one file

combineAudio

Optional

Additionally joins all clips into a single combined.mp3 (and one continuous subtitle file) in the original order — handy for full videos, podcasts or audiobooks.

Type:boolean

Default:false

Parallel conversions

maxConcurrency

Optional

How many texts are converted at the same time. 5 is a safe default; raise it for large batches.

Type:integer

Minimum:1

Maximum:20

Default:5

List all voices (no audio)

listVoices

Optional

Run once with this ON to export the full catalog of 322 voices (name, language, gender, personality) to the dataset — then pick your favorite and put its code into 'Custom voice code'. Free, no characters charged.

Type:boolean

Default:false

Text to Speech — 300+ Neural Voices, Free MP3

hipersoft/text-to-speech

Convert any text to natural-sounding speech as an MP3 download. 300+ premium neural voices across 70+ languages, adjustable rate, pitch and volume. Great for voiceovers, videos, accessibility and audio content. No setup.

hiper soft

Text To Speech

vivid_astronaut/text-to-speech

Convert text to natural speech using AI voices. Multiple voices and languages available. Generate audio files for podcasts, videos, accessibility, and voice assistants.

BRAINIALL Team

Video & Audio Transcriber - Speech to Text, Subtitles & SRT

zaver.api/universal-video-audio-transcriber

Transcribe any video or audio to text from a URL - YouTube, TikTok, Facebook, X, Vimeo, podcasts, 1000+ sites, or direct media files. AI speech-to-text with language detection, timestamps and ready-to-use SRT/WebVTT subtitles. Optional AI summary. Export to CSV, JSON or Excel.

Zaver

TikTok Transcript Scraper - AI Speech-to-Text & SRT

deapi/tiktok-transcript-scraper

Transcribes the audio with an AI speech model - not TikTok's auto-captions, so it works when a video has none. Word-level timestamps, speaker labels, SRT and VTT subtitles, 90+ languages. No TikTok login or API key needed.

deAPI

5.0

Video & Audio Transcriber · Whisper Speech-to-Text, SRT & VTT

blackfalcondata/video-audio-transcriber

Whisper speech-to-text for any video, audio or podcast URL: full transcript with timestamped segments plus SRT/VTT subtitles, 99+ languages auto-detected. Works on YouTube and TikTok links, podcast RSS feeds and direct media files with no API key needed.

Black Falcon Data

Text To Speech (NO API)

dead00/text-to-speech-no-api

Convert text to natural speech in 43 curated voices across 8 languages. Clone any voice from a 15-second sample. Long text splits automatically. No API key, no subscription — pay only for what you convert.

Dead

YouTube Channel Subtitles Downloader (SRT/VTT)

crawlyard/youtube-channel-subtitles

Download SRT/VTT subtitles for a whole YouTube channel from one URL or @handle — plus plain text for every video.

Crawlyard Data

Speech to Text — YouTube, TikTok, Instagram, 99+ Languages

andronixmd/speech-to-text-transcriber

Multi-engine speech-to-text for YouTube, TikTok, Instagram, podcasts, X, and direct media URLs. Auto-detects 99+ languages, routes across Groq/OpenAI/ElevenLabs/Google with automatic failover, and returns text, SRT/VTT subtitles, and optional speaker diarization. Pay-per-event — no subscription.