English text to speech with natural voices
Turn English texts into natural voice-overs with the standard model, the cheapest option, billed per 100 characters. Choose a female or male voice and the speed. Each text returns an MP3 file (64 kb/s) with its URL, duration and character count.
Input
Output fields
Sign up on Apify or log in
The Text to Speech API — Batch, 36 Languages, Pay per Character Actor is ready to run with the inputs already set for "English text to speech with natural voices". Sign up or log in and you'll land in Apify Console with a copy of this exact task.
Start the "English text to speech with natural voices" task
The Text to Speech API — Batch, 36 Languages, Pay per Character Actor will start running based on the input automatically. You can also change all the input fields, like texts, language, and more, to match your specific use case.
Receive the "English text to speech with natural voices" output
Monitor the progress in real time. You will be notified as soon as your dataset is complete and ready for review. Each result includes data such as audio, subtitles, text, and more.
Integrate into your workflow
The final output is delivered in JSON, CSV, or Excel format, ready to be plugged into your workflow. You can also run the "English text to speech with natural voices" task via API.

Integrate "English text to speech with natural voices" into your workflow
Connect "English text to speech with natural voices" with 100+ integrations, or run it via API or MCP.
Webhook
n8n
Make
Zapier
Airbyte
Keboola
IFTTT
Hubspot
GDrive
Gmail
Apify MCP
GitHub
Slack
LangChain
LlamaIndex
Flowise
Pinecone
OpenAI
Mastra
Clay
This English text to speech task uses the standard Kokoro model at $0.005 per started 100 characters on the free plan, from $0.006 on paid plans. Set quality to premium for MiniMax at $0.012 per 100.
This English text to speech task takes female or male, or a Kokoro voice id such as af_heart, am_michael, bf_emma or bm_george for American and British accents.
This English voice-over task outputs MP3 at 64 kb/s mono, about 80 KB for 10 seconds, or 16-bit WAV for editing. Both cost the same: only the characters voiced are billed.
An agent can run this English text to speech task through the Apify MCP server and read the dataset items back, each holding the audio URL in outputUrl. Nothing in the input is required.