voice-clone-ttsdefaultVoice Clone TTS API — how to connect and pay
Voice cloning — speech in YOUR own voice. Upload a short recording of your voice (3–60 seconds, wav/mp3) with POST /api/media/voices or in the studio, get a voice_id and synthesise any text with it, Russian included. A standard voice is free to create. A Premium voice gives the closest likeness: a 10–60 second recording, $2.00 once at creation, synthesis with the MiniMax Speech 02, 2.6 and 2.8 engines (HD and Turbo). Synthesis is priced per 1000 characters. Up to 4000 characters per request.
Channel comparison
last 7 days
| Channel | Price |
|---|---|
Dune voice-clone-ttsdefault | from $0.001333 / 1,000 chars |
Build the result you need
voice-clone-ttsThis model only publishes its minimum price in the catalog.
What is Voice Clone TTS
Voice cloning — speech in YOUR own voice. Upload a short recording of your voice (3–60 seconds, wav/mp3) with POST /api/media/voices or in the studio, get a voice_id and synthesise any text with it, Russian included. A standard voice is free to create. A Premium voice gives the closest likeness: a 10–60 second recording, $2.00 once at creation, synthesis with the MiniMax Speech 02, 2.6 and 2.8 engines (HD and Turbo). Synthesis is priced per 1000 characters. Up to 4000 characters per request.
Contract at a glance
- Input
- text
- Output
- audio
- Mode
- async (job + polling)
- Status polling
- every 3 s · up to 90 s
Strengths
- Pricing: per 1K characters
- Inputs: text
- 8 configurable options
- One API key for media generation
Where it is used
- Video voiceovers
- Voice scripts
- Audio versions of text
- Recording cleanup
API contract
Generation runs asynchronously: create a job, then poll its status until completion.
- Create job
- POST /api/media/generate
- Check status
- GET /api/media/jobs/{jobId}
- Input
- text
- Output
- audio
- Polling
- every 3 s · up to 90 s
- Authentication
- Authorization: Bearer sk-pv-…
Example request
Pass your key in the Bearer header. The API returns jobId for polling the status.
curl -sS https://getvibeapi.com/api/media/generate \
-H "Authorization: Bearer $GETVIBE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary '{"model":"voice-clone-tts","prompt":"a beautiful landscape","opts":{"voice_id":"example","engine":"qwen3","language":"auto","response_format":"mp3"}}'JavaScript
const response = await fetch('https://getvibeapi.com/api/media/generate', {
method: 'POST',
headers: {
Authorization: `Bearer ${process.env.GETVIBE_API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
"model": "voice-clone-tts",
"prompt": "a beautiful landscape",
"opts": {
"voice_id": "example",
"engine": "qwen3",
"language": "auto",
"response_format": "mp3"
}
}),
});
if (!response.ok) throw new Error(`GetVibe API: ${response.status}`);
const { jobId } = await response.json();
console.log(jobId);API request parameters
Parameters for requests to Voice Clone TTS via the GetVibe API.
promptreq.voice_idreq.enginelanguageinstructstabilitysimilarity_boostseedprevious_textnext_textapply_text_normalizationemotionspeedpitchvolumevoice_modify_pitchvoice_modify_timbrevoice_modify_intensityresponse_formatsample_ratebitratechannelprevious_request_idsnext_request_idspronunciation_dictvoice_modify| Parameter | Type | Values | Default | Price |
|---|---|---|---|---|
promptreq. | text | text description | required | — |
voice_idreq. | text / number | any value | — | Included in the base price |
engine | option selection | Qwen3-TTS — best quality (default) · Chatterbox — economy · MiniMax Speech 02 HD — Premium, closest likeness · MiniMax Speech 02 Turbo — Premium, faster and cheaper · MiniMax Speech 2.6 HD — Premium · MiniMax Speech 2.6 Turbo — Premium, faster and cheaper · MiniMax Speech 2.8 HD — Premium, with sounds (laughs, sighs) · MiniMax Speech 2.8 Turbo — Premium, faster and cheaper · ElevenLabs v4 — $0.16 per 1000 characters · ElevenLabs v4 Turbo — $0.08 per 1000 characters | Qwen3-TTS — best quality | Included in the base price |
language | option selection | Auto (default) · Russian · English · German · French · Spanish · Italian · Portuguese · Chinese · Japanese · Korean | Auto | Included in the base price |
instruct | text / number | any value | — | Included in the base price |
stability | text / number | any value | — | Included in the base price |
similarity_boost | text / number | any value | — | Included in the base price |
seed | text / number | any value | — | Included in the base price |
previous_text | text / number | any value | — | Included in the base price |
next_text | text / number | any value | — | Included in the base price |
apply_text_normalization | option selection | auto (default) · on · off | auto | Included in the base price |
emotion | option selection | Auto (from the text) (default) · Neutral · Happy · Sad · Angry · Fearful · Disgusted · Surprised | Auto (from the text) | Included in the base price |
speed | text / number | any value | — | Included in the base price |
pitch | text / number | any value | — | Included in the base price |
volume | text / number | any value | — | Included in the base price |
voice_modify_pitch | text / number | any value | — | Included in the base price |
voice_modify_timbre | text / number | any value | — | Included in the base price |
voice_modify_intensity | text / number | any value | — | Included in the base price |
response_format | option selection | MP3 (default) · WAV · FLAC · Opus · PCM (raw 16-bit) | MP3 | Included in the base price |
sample_rate | option selection | Standard (32000 Hz) (default) · 8000 Hz · 16000 Hz · 22050 Hz · 24000 Hz · 32000 Hz · 44100 Hz · 48000 Hz | Standard (32000 Hz) | Included in the base price |
bitrate | option selection | Standard (128 kbps) (default) · 32 kbps · 64 kbps · 128 kbps · 256 kbps | Standard (128 kbps) | Included in the base price |
channel | option selection | Standard (mono) (default) · Mono · Stereo | Standard (mono) | Included in the base price |
previous_request_ids | Array<strings>, 0–3 items | 1–3 items | — | Included in the base price |
next_request_ids | Array<strings>, 0–3 items | 1–3 items | — | Included in the base price |
pronunciation_dict | Array<strings>, 0–100 items | 1–100 items | — | Included in the base price |
voice_modify | text | Voice modification (pitch, timbre, intensity) | — | Included in the base price |
Request: POST https://getvibeapi.com/api/media/generate. Prices in USD.
Price of Voice Clone TTS
The cost of Voice Clone TTS: from $0.026667 per 1K characters. The price is calculated dynamically at the current exchange rate, and the final charge is shown in the API response (priceRub). Payment in USD, no subscriptions.
What a default request costs
With no parameters sent, the request uses these values: Engine — Qwen3-TTS — best quality, Language — Auto, Spell out numbers and dates — auto, Emotion — Auto (from the text). That request costs $0.026667.
Channels and prices for every parameter combination
For every channel, the price of every parameter combination. It is exactly the amount a successful generation is charged, and the same figure as in the machine-readable table linked below.
Dunevoice-clone-ttsfrom $0.001333 / 1,000 charsexact prices
| Engine · Language \ Format | MP3 | WAV | FLAC | Opus | PCM (raw 16-bit) |
|---|---|---|---|---|---|
| Qwen3-TTS — best quality · Auto | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Russian | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · English | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · German | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · French | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Spanish | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Italian | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Portuguese | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Chinese | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Japanese | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Qwen3-TTS — best quality · Korean | $0.026667 / 1,000 chars | $0.026667 / 1,000 chars | — | — | — |
| Chatterbox — economy · Auto | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Russian | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · English | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · German | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · French | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Spanish | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Italian | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Portuguese | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Chinese | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Japanese | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| Chatterbox — economy · Korean | $0.001333 / 1,000 chars | $0.001333 / 1,000 chars | — | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Auto | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Russian | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · English | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · German | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · French | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Spanish | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Italian | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Portuguese | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Chinese | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Japanese | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 HD — Premium, closest likeness · Korean | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Auto | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Russian | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · English | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · German | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · French | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Spanish | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Italian | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Portuguese | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Chinese | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Japanese | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 02 Turbo — Premium, faster and cheaper · Korean | $0.08 / 1,000 chars | — | $0.08 / 1,000 chars | — | — |
| MiniMax Speech 2.6 HD — Premium · Auto | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 2.6 HD — Premium · Russian | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 2.6 HD — Premium · English | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
| MiniMax Speech 2.6 HD — Premium · German | $0.133333 / 1,000 chars | — | $0.133333 / 1,000 chars | — | — |
Price per 1,000 characters of text. The charge is this price × the number of characters.
The first rows are shown; every combination is in the table linked below.
Every combination as JSON: /api/media/price-table?model=voice-clone-tts
README
The machine-readable contract for Voice Clone TTS contains the request schema, operations, limits, polling and response examples.
# Voice Clone TTS
Public model: voice-clone-tts
Create job: POST /api/media/generate
Check status: GET /api/media/jobs/{jobId}
## Input parameters
- `prompt` (text): text description; default: required
- `voice_id` (text / number): any value; default: —
- `engine` (option selection): Qwen3-TTS — best quality (default) · Chatterbox — economy · MiniMax Speech 02 HD — Premium, closest likeness · MiniMax Speech 02 Turbo — Premium, faster and cheaper · MiniMax Speech 2.6 HD — Premium · MiniMax Speech 2.6 Turbo — Premium, faster and cheaper · MiniMax Speech 2.8 HD — Premium, with sounds (laughs, sighs) · MiniMax Speech 2.8 Turbo — Premium, faster and cheaper · ElevenLabs v4 — $0.16 per 1000 characters · ElevenLabs v4 Turbo — $0.08 per 1000 characters; default: Qwen3-TTS — best quality
- `language` (option selection): Auto (default) · Russian · English · German · French · Spanish · Italian · Portuguese · Chinese · Japanese · Korean; default: Auto
- `instruct` (text / number): any value; default: —
- `stability` (text / number): any value; default: —
- `similarity_boost` (text / number): any value; default: —
- `seed` (text / number): any value; default: —
- `previous_text` (text / number): any value; default: —
- `next_text` (text / number): any value; default: —
- `apply_text_normalization` (option selection): auto (default) · on · off; default: auto
- `emotion` (option selection): Auto (from the text) (default) · Neutral · Happy · Sad · Angry · Fearful · Disgusted · Surprised; default: Auto (from the text)
- `speed` (text / number): any value; default: —
- `pitch` (text / number): any value; default: —
- `volume` (text / number): any value; default: —
- `voice_modify_pitch` (text / number): any value; default: —
- `voice_modify_timbre` (text / number): any value; default: —
- `voice_modify_intensity` (text / number): any value; default: —
- `response_format` (option selection): MP3 (default) · WAV · FLAC · Opus · PCM (raw 16-bit); default: MP3
- `sample_rate` (option selection): Standard (32000 Hz) (default) · 8000 Hz · 16000 Hz · 22050 Hz · 24000 Hz · 32000 Hz · 44100 Hz · 48000 Hz; default: Standard (32000 Hz)
- `bitrate` (option selection): Standard (128 kbps) (default) · 32 kbps · 64 kbps · 128 kbps · 256 kbps; default: Standard (128 kbps)
- `channel` (option selection): Standard (mono) (default) · Mono · Stereo; default: Standard (mono)
- `previous_request_ids` (Array<strings>, 0–3 items): 1–3 items; default: —
- `next_request_ids` (Array<strings>, 0–3 items): 1–3 items; default: —
- `pronunciation_dict` (Array<strings>, 0–100 items): 1–100 items; default: —
- `voice_modify` (text): Voice modification (pitch, timbre, intensity); default: —
## Public variants
- `voice-clone-tts`: DuneFAQ about the Voice Clone TTS API
How much does Voice Clone TTS cost?
The price of Voice Clone TTS: from $0.026667 per 1K characters. The price is calculated dynamically at the current exchange rate.
Is it compatible with the OpenAI SDK?
Yes, the API is fully OpenAI-compatible. Just change base_url to https://getvibeapi.com/v1 and set your key — the rest of the code stays the same.
Connect Voice Clone TTS right now
Sign up in a minute, pay per use, ready-made code above.
Get API key