Video and ads
A voice for clips and presentations without a studio.
> Voice a 30-second ad> open voice --ru_
Text speech with a model without a VPNElevenLabs, Gemini TTS, MiniMax Speech, and 30 more text-to-speech models in one window
Lifelike voices for video, podcasts, audiobooks, and voice assistants. Pay via SBP, and pay only for minutes of speech.
- Eleven v4$0.16
- Eleven Multilingual v2$0.16
- Eleven Flash v2.5$0.08
- Gemini 3.8 Flash Lite TTS$0.018
ElevenLabsGeminiMiniMax
> you: Voice a greeting for an answering machine
gemini-3.8-flash-tts ▸ voice: female, calm
[ok] 8 sec of speech · charged $0.0036
> ls ./voice
Speech models in the aggregator
The aggregator has 34 text-to-speech models:
ElevenLabsThe most lifelike and emotional voices, multilingual models.Learn more →HeyGenHeyGen Voice — a voice for clips and avatars.Learn more →
Gemini TTSVoiceover from Google: Gemini 3.8 Flash TTS and Flash Lite TTS.
MiniMax SpeechSpeech 2.8 HD and Turbo — for clips and audiobooks.
And othersFish Audio, Microsoft MAI-Voice, Qwen TTS, Deepgram Aura, Grok Voice, and others — in the table.
> voice --choose
Which speech model should you choose
Go by the task: there's no need to pay for the most expensive model where a simpler one will do.
- The most lifelike speechIntonation and emotion are set right in the text.Eleven v4$0.16per minute of voiceover
- Long texts and audiobooksSmooth, natural voiceover, including in Russian.Eleven Multilingual v2$0.16per minute of voiceover
- Voice assistantAlmost no delay.Eleven Flash v2.5$0.08per minute of voiceover
- InexpensiveFast Google voiceover at a low price.Gemini 3.8 Flash Lite TTS$0.018per minute of voiceover
- A voice for an avatar videoSpeech for HeyGen clips.HeyGen Voice$0.03per minute of voiceover
> voice --help
What speech models can do
Audiobooks and podcasts
Long texts — smooth and natural.
> Voice a book chapterVoice bots
Fast answers for assistants and call centers.
> A voice for an answering machineTraining
Speech for courses and manuals.
> Voice an Excel lesson> price voice --beta 1.0
How much does voiceover cost
No subscription: pay only for text-to-speech. The price is from $0.0012 to $0.30 per minute of speech.
Beta 1.0 prices may change
| Model | Developer | Minute of voiceover | Hour of voiceover | $10 is enough for |
|---|---|---|---|---|
| HeyGen Voice | HeyGen | $0.03 | $1.80 | ≈ 333 min |
| HeyGen Voice Turbo | HeyGen | $0.008 | $0.48 | ≈ 1,250 min |
| Drama 3 | Fish Audio | $0.004 | $0.24 | ≈ 2,500 min |
| Eleven v4 | ElevenLabs | $0.16 | $9.60 | ≈ 62 min |
| Eleven v4 Turbo | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| Eleven v3 | ElevenLabs | $0.16 | $9.60 | ≈ 62 min |
| Eleven v3 Conversational | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| Eleven Flash v2.5 | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| Eleven Turbo v2 | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| Eleven Multilingual v2 | ElevenLabs | $0.16 | $9.60 | ≈ 62 min |
| Eleven Turbo v2.5 | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| Eleven Flash v2 | ElevenLabs | $0.08 | $4.80 | ≈ 125 min |
| MAI-Voice-2.1-Flash | Microsoft AI | $0.03 | $1.80 | ≈ 333 min |
| MAI-Voice-2.1 | Microsoft AI | $0.044 | $2.64 | ≈ 227 min |
| Seed Audio 1.0 | ByteDance Seed | $0.30 | $18.00 | ≈ 33 min |
| Gemini 3.8 Flash Lite TTS | $0.018 | $1.10 | ≈ 546 min | |
| Gemini 3.8 Flash TTS | $0.027 | $1.64 | ≈ 366 min | |
| Flux TTS | Deepgram | $0.09 | $5.40 | ≈ 111 min |
| S1 | Fish Audio | $0.03 | $1.80 | ≈ 333 min |
| S2 Pro | Fish Audio | $0.03 | $1.80 | ≈ 333 min |
| S2.1 Pro | Fish Audio | $0.03 | $1.80 | ≈ 333 min |
| MAI-Voice-2-Flash | Microsoft AI | $0.03 | $1.80 | ≈ 333 min |
| Qwen-Audio-3.0-TTS Flash | Qwen | $0.03 | $1.80 | ≈ 333 min |
| Qwen-Audio-3.0-TTS Plus | Qwen | $0.04 | $2.40 | ≈ 250 min |
| Aura-2 | Deepgram | $0.06 | $3.60 | ≈ 166 min |
| Speech 2.8 HD | MiniMax | $0.20 | $12.00 | ≈ 50 min |
| Speech 2.8 Turbo | MiniMax | $0.12 | $7.20 | ≈ 83 min |
| MAI-Voice-2 | Microsoft AI | $0.044 | $2.64 | ≈ 227 min |
| Grok Voice TTS 1.0 | SpaceXAI | $0.03 | $1.80 | ≈ 333 min |
| Gemini 3.1 Flash TTS Preview | $0.061 | $3.64 | ≈ 165 min | |
| CSM 1B | Sesame | $0.014 | $0.84 | ≈ 714 min |
| Orpheus 3B | Canopy Labs | $0.014 | $0.84 | ≈ 714 min |
| Kokoro 82M | hexgrad | $0.0012 | $0.072 | ≈ 8,333 min |
| Voxtral Mini TTS | Mistral | $0.032 | $1.92 | ≈ 312 min |
A minute of speech is about 1000 characters of text. The actual generation cost is deducted from your balance.
> cat ./how-to-start.txt
How to voice text with a model in Russia
- 01
Sign up for P2D
One account opens all the aggregator's models — no need to register with each one separately.
- 02
Top up your balance via SBP
Balance in dollars. No foreign card or VPN needed, no monthly fee.
- 03
Choose a speech model
Open the AI aggregator, choose a model, and paste the text to be voiced. The cost of the result is deducted from your balance.
> man voice
Frequently asked questions about voiceover models
Which model voices Russian best?
Most people choose ElevenLabs' multilingual models — Eleven Multilingual v2 and Eleven v3. Try several voices and compare.
How much does a minute of speech cost?
From $0.0012 to $0.30 per minute — depends on the model. A minute is roughly 1000 characters of text.
Is a VPN needed?
No. The P2D aggregator opens from Russia without a VPN, and the service itself sends the requests to the models.
How to pay?
Top up your balance in dollars via SBP with a Russian card. No foreign card needed, and there's no subscription or monthly fee — you're charged only for what you generate.
Other models in the aggregator
> start --voice
Voice your first text right now
Sign up in a minute, top up via SBP, pay only for the result.