Oxyy is an independent API gateway, not affiliated with ElevenLabs.
On Oxyy, ElevenLabs text to speech starts at $0.0088 per 1K characters (Eleven v4), speech to text starts at $0.088 per hour of audio (Scribe v2) and music and sound generation starts at $0.048 per minute of generated audio (Sound Effects v2), pay as you go. Eleven v3 costs $0.040 per 1K characters, pay-as-you-go (standard price $0.100 per 1K characters).
| Model | Type | Price | Saving | Released |
|---|---|---|---|---|
| Eleven v3eleven_v3 | Text to speech | Standard price $0.100, on Oxyy $0.040per 1K characters | 60% | Feb 1, 2026 |
| Eleven Multilingual v2eleven_multilingual_v2 | Text to speech | Standard price $0.100, on Oxyy $0.040per 1K characters | 60% | — |
| Eleven Flash v2.5eleven_flash_v2_5 | Text to speech | Standard price $0.050, on Oxyy $0.020per 1K characters | 60% | — |
| Scribe v2scribe_v2 | Speech to text | Standard price $0.220, on Oxyy $0.088per hour of audio | 60% | — |
| Eleven v4eleven_v4 | Text to speech | Standard price $0.022, on Oxyy $0.0088per 1K characters | 60% | Sep 28, 2026 |
| Eleven Flash v2eleven_flash_v2 | Text to speech | Standard price $0.050, on Oxyy $0.020per 1K characters | 60% | — |
| Dubbing v1eleven_dubbing_v1 | Text to video | Standard price $0.330, on Oxyy $0.132per minute of input media | 60% | — |
| Dubbing v2eleven_dubbing_v2 | Text to video | Standard price $2.20, on Oxyy $0.880per minute of input media | 60% | — |
| Eleven English v2 (Voice Changer)eleven_english_sts_v2 | Text to speech | Standard price $0.120, on Oxyy $0.048per minute of input | 60% | — |
| Eleven Multilingual v2 (Voice Changer)eleven_multilingual_sts_v2 | Text to speech | Standard price $0.120, on Oxyy $0.048per minute of input | 60% | — |
| Eleven Music v2music_v2 | Music and sound generation | Standard price $0.150, on Oxyy $0.060per minute of generated audio | 60% | — |
| Eleven Music v2.5music_v2_5 | Music and sound generation | Standard price $0.150, on Oxyy $0.060per minute of generated audio | 60% | — |
| Eleven v3 Conversationaleleven_v3_conversational | Text to speech | Standard price $0.050, on Oxyy $0.020per 1K characters | 60% | — |
| ElevenAgents Speech Engineeleven_speech_engine | Text to speech | Standard price $0.080, on Oxyy $0.032per minute of input | 60% | — |
| Scribe v2 Medicalscribe_v2_medical | Speech to text | Standard price $0.220, on Oxyy $0.088per hour of audio | 60% | — |
| Scribe v2 Realtimescribe_v2_realtime | Speech to text | Standard price $0.390, on Oxyy $0.156per hour of audio | 60% | — |
| Sound Effects v2eleven_text_to_sound_v2 | Music and sound generation | Standard price $0.120, on Oxyy $0.048per minute of generated audio | 60% | — |
| Voice Isolatoreleven_voice_isolator | Speech to text | Standard price $0.120, on Oxyy $0.048per minute of audio | 60% | — |
| Eleven Multilingual v2 (Voice Design)eleven_multilingual_ttv_v2 | Text to speech | Not yet priced | — | — |
| Eleven v3 (Voice Design / Text to Voice)eleven_ttv_v3 | Text to speech | Not yet priced | — | — |
On Oxyy, Eleven v3 costs $0.040 per 1K characters at the pay-as-you-go price (standard price $0.100 per 1K characters). Text to speech starts at $0.0088 per 1K characters, speech to text starts at $0.088 per hour of audio and music and sound generation starts at $0.048 per minute of generated audio. There is no subscription: you pay only for what you use.
For text to speech billed per 1K characters, Eleven v4 is the lowest-priced ElevenLabs model on Oxyy, at $0.0088 per 1K characters. Prices for other model types use different units, so compare within a type.
Yes. Oxyy's API is OpenAI-compatible: set the base URL to https://api.oxyy.ai/v1, use your Oxyy API key and pass the model id, for example "eleven_v3", to /v1/audio/speech. Transcription models use /v1/audio/transcriptions and video models use /v1/videos/generations.
No. Oxyy is an independent API gateway, not affiliated with or endorsed by ElevenLabs. It gives you one API key and one bill for models from many AI labs, ElevenLabs among them.
Lifelike, consistent-quality speech synthesis. The most stable model for long-form generation, with consistent voice quality and accent across language switches.
ElevenLabs' flagship speech synthesis model: 90+ languages, 10,000-character requests, multi-speaker dialogue, audio tags, inline IPA pronunciation control and Professional Voice Clone support.
State-of-the-art batch speech recognition across 90+ languages, with precise word-level timestamps, speaker diarization and dynamic audio tagging.
ElevenLabs' most emotionally rich, expressive speech synthesis model. Natural, life-like speech with high emotional range and contextual understanding, and support for natural multi-speaker dialogue.
ElevenLabs' fastest speech synthesis model, built for real-time applications and the Agents Platform. Balances speed and quality at half the price per character.
English-only ultra-fast speech synthesis model.
Dubs video with automatic speaker detection across 29 languages.
End-to-end dubbing model that preserves voice and emotion across 92 languages.
English-only voice changer model.
State-of-the-art multilingual voice changer. Converts an existing recording into another voice while preserving delivery.
State-of-the-art multilingual voice designer model.
Studio-grade music generation from text prompts, composition plans and previously generated songs.
ElevenLabs' most advanced music model. Studio-grade generation from text prompts, composition plans and previously generated songs, with richer melodies, deeper arrangements and more layered instruments than music_v2.
Human-like and expressive voice DESIGN model. Generates a new voice from a text description rather than speech from text.
ElevenLabs' most expressive realtime speech synthesis model, tuned for low-latency conversation while keeping v3's emotional range.
ElevenLabs' speech models combined in one low-latency agent pipeline, for adding voice to a chat agent.
A fine-tune of Scribe v2 for medical and clinical audio. Improves recognition of drug names, anatomy, pathology and clinical dictation while matching Scribe v2 on everyday speech.
ElevenLabs' fastest and most accurate live speech recognition model, delivering partial transcriptions in about 150ms across 90+ languages.
Royalty-free sound effects generation from text prompts.
Removes background noise, ambient sounds, reverb and interference to leave clean dialogue.
