Transparent pricing with no hidden fees. Pay as you go.
elevenlabs-v4-tts| Model | Spec | PoYo price | Official price | You save |
|---|---|---|---|---|
| elevenlabs-v4-tts | Text to speech | $0.080 16 credits per 1000 characters | - | - |
* Actual fees are based on the final output.
Expressive multilingual speech, directed with audio tags
From character performances to multilingual narration, hear how scripts become natural speech.
01
Give each line its own delivery by writing direction into text. Eleven v4 interprets audio tags alongside your script, adding reactions such as chuckles and laughter where the scene calls for them. Bring character to a story or an advertising read while keeping the spoken words and performance direction together.
02
Reach listeners in their own language with speech that preserves natural rhythm and expression. Eleven v4 supports more than 90 languages; use language_code to specify a language or leave it unset for automatic detection. Produce versions for different markets within the same narration workflow.
03
Start with a voice that suits your script, from a warm storyteller to a clear explainer. Set voice for the speaker, then adjust stability and similarity_boost to guide the output. Build a narration workflow for audiobooks, lessons and video voiceovers without recording each take yourself.
Turn chapters into expressive narration with Eleven v4. Choose a narrator, add direction to character lines and generate each passage within the 5,000-character request limit. Keep a consistent voice choice throughout your production workflow.
Create voiceovers for explainers, product walkthroughs and social videos with Eleven v4. Revise the script without scheduling another recording session, and request optional timestamps when available to help align speech with the edit.
Give campaign copy an appropriate delivery, from an energetic launch to a warm introduction. Use Eleven v4 audio tags to direct the reading, then produce different scripts with the same selected voice for a consistent campaign sound.
Turn written explanations in courses, tutorials, and training materials into clear speech. Use Eleven v4 voice selection and text normalization settings to handle numbers, dates, and abbreviations as needed, creating reusable educational content.
Produce narration for audiences in different languages with Eleven v4. Supply the localized text and optional language code, then listen to the result before publishing. The model supports more than 90 languages for global content workflows.
Give individual character lines emotion through audio tags and a chosen voice. Eleven v4 fits scripted dialogue, quest narration and scene introductions. Generate one speaker per request and assemble the completed audio in your game production pipeline.
Step 1: Register and Create an API Key
Sign in to PoYo and create a key for your application.
Create API Key →
Step 2: Add Credits
Top up for your expected usage and check the Playground estimate before each request.
Add Credits →
Step 3: Integrate the Async API
Submit an elevenlabs-v4-tts request, save task_id and poll for the audio and optional timestamp files.
Read the API Documentation →
Use the same submission and status workflow as other PoYo models. Track the returned task ID and collect completed audio without integrating a separate provider protocol.
Pay for the characters you submit. Check the proportional request estimate before running, with no rounding to full blocks of 1,000 characters.
Prepare requests through forms or JSON. Both methods use the same parameter validation, default values and cost calculation rules, making it easy to move from testing to integration.
Download the original audio format and a separate timestamp JSON when available. Move the resulting files directly into your editing or application workflow.
