Transparent pricing with no hidden fees. Pay as you go.
elevenlabs-v4-turbo-tts| Model | Spec | PoYo price | Official price | You save |
|---|---|---|---|---|
| elevenlabs-v4-turbo-tts | Text to speech | $0.040 8 credits per 1000 characters | - | - |
* Actual fees are based on the final output.
Natural multilingual voiceovers with audio tags and voice controls
Direct the performance, reach more audiences and give spoken replies a natural rhythm.
01
Give lines the delivery suited to their context. Add audio tags to your script to guide emotion, pauses, laughter and other vocal reactions, adding energy to ads, creating atmosphere for stories and giving characters distinctive expression. You can also adjust voice stability and similarity in the same request.
02
Bring your message to audiences in their own language. Eleven v4 Turbo supports speech across 90+ languages, helping teams create localized lessons, product explainers and spoken updates. Specify a language when needed and build each version through the same familiar text-to-speech workflow.
03
Create clear and natural voice replies for customer confirmations, booking notifications and interactive assistants. Eleven v4 Turbo is optimized for conversational speech while preserving rich expressive ability, helping even short responses fit the situation. Connect generated audio to your product workflow and provide users with easier-to-understand spoken information.
Turn scripts into engaging spoken content with Eleven v4 Turbo. Use emotion and pause tags for stories, podcasts and short videos, then download the audio for your editing workflow.
Produce voiceovers for product launches, explainers and campaigns with Eleven v4 Turbo. Guide the tone in your script and prepare versions for different messages, channels and audiences.
Create spoken versions of translated content with Eleven v4 Turbo. Support regional onboarding, announcements and product guidance with multilingual delivery and optional language selection.
Use Eleven v4 Turbo to add clear narration to courses, exercises and training materials. Combine pause tags and a consistent voice to help learners follow each teaching step, then integrate the audio into educational content.
Explore expressive character lines, narrative cues and spoken instructions with Eleven v4 Turbo. Direct each line through text and audio tags, then integrate the audio into your production tools.
Create spoken confirmations, notifications and assistant replies with Eleven v4 Turbo. Retrieve audio through PoYo's task workflow and choose formats suited to your application or telephony pipeline.
Compare the official models' intended use and speech controls to choose a starting point for your product.
| Model capability | Eleven v4 Turbo | Gemini 3.8 Flash TTS |
|---|---|---|
| Model focus | Expressive speech optimized for real-time conversations and voice agents | Creative speech production, expressive acting and multi-speaker narration |
| Language coverage | 90+ languages | 130+ languages |
| Expression controls | Inline audio tags for emotion, delivery and vocal reactions | Turn-level speech metadata and inline vocal tags |
Based on the vendors' official model documentation, reviewed October 13, 2026. This compares native model capabilities. PoYo currently exposes Eleven v4 Turbo through asynchronous tasks with a 5,000-character request limit.
Step 1: Create an API Key
Sign in to PoYo and create a key for your application. Keep it on your server when integrating the API.
Create API Key →
Step 2: Add Credits
Top up your balance and review the pricing table above. The Playground estimates credits from the exact text you submit, helping you control your usage budget.
Add Credits →
Step 3: Submit Your Script
Send your text and voice settings, save the task ID and retrieve the finished audio. When completion notifications are needed, configure a callback URL.
View API Reference →
Review the per-character rate and estimate credits before running your script. The pricing table and Playground share the same model rates, making it easier to budget audio work.
Prepare requests in a form or JSON editor using the supported parameter names, formats and limits. Inspect the response and download your audio before integrating the same request into your application.
Use your PoYo API key to access the models available to your account. Keep authentication familiar as you add speech generation alongside other model workflows in your application.
Track each submitted script with a task ID, query its status and receive completion notifications through callbacks. Handle generated audio and optional timing files through a consistent task workflow.
