OpenSpeaker Voice Changer
openspeaker.ai
- Web
- API
6.9 Club score Visit openspeaker.ai
Plans
Every plan and price1 month
$5 one-time
3 months
$5 one-time
9 months
$5 one-time
No expiry
$5 one-time
What the maker publishes
- AI training
- Eligible prompts, inputs, outputs and technical records may be used for evaluation and improvement, while identifiable voice samples require permission or another lawful basis for training. source
- API access
- Yes source
- API authentication
- Requests use the https://api.openspeaker.ai base URL and an xi-api-key header. source
- API documentation
- The developer site provides a machine-readable text guide and an OpenAPI JSON document. source
- API endpoint
- The public API exposes voice conversion through POST /v1/task/voice-changer. source
- API extensibility
- The API also exposes endpoints for speech, dialogue, dictionaries, voice cloning, dubbing, isolation, transcription, sound effects, music and image generation. source
- API integration
- Voice Changer is available through the asynchronous POST /v1/task/voice-changer API, which returns a task_id for polling or webhook delivery. source
- API workflow
- API jobs return a task ID that can be polled or completed through a webhook callback. source
- Catalog scope
- The public catalog contains 11 active tools, 20 image models and five voice sources. source
- Company headquarters
- The public pages opened do not state a headquarters location. source
- Connected integration
- The voice changer identifies ElevenLabs as its connected service. source
- Connected service
- The voice-changing workflow identifies ElevenLabs as its connected service. source
- Controls
- Users can adjust stability, similarity, style, speaker boost, noise removal and transcript options. source
- Conversion models
- The available conversion models are Eleven Multilingual v2 and English v2. source
- Core function
- Voice Changer transforms recorded speech into another voice with ElevenLabs speech-to-speech while retaining the original performance and pacing. source
- Credit estimate
- The maker estimates that 1,000,000 credits provide about 1,700 minutes at its low-cost TTS tier, with actual use varying by settings. source
- Data processing
- The AI Data Use Policy says minimum necessary inputs may be transmitted to the connected provider selected by the tool or routing logic. source
- Data sharing
- OpenSpeaker may send task content and settings to the connected provider needed to complete a selected workflow, including providers outside Vietnam. source
- Duration limit
- Each voice-changing file can be up to 5 hours long. source
- Duration limit
- Each uploaded file can be up to five hours long. source
- Export formats
- MP3 source
- File-size limit
- The effective direct-request upload cap is 200 MB. source
- Founded year
- The public pages opened do not state a founding year. source
- Free plan
- No source
Checked against the maker's pages on 15 Oct 2026.