Responses are generated using AI and may contain mistakes.
Bland is getting a major upgrade. We're working on updating our docs as users transition in the coming weeks. Reach out to support@bland.ai with questions.
{ "models": [ { "model_id": "BTTS_V2", "display_name": "V2", "description": "Previous-generation TTS with multilingual output and instant single-sample cloning. Prefer V3 where its language support fits.", "sample_rates": [8000, 16000, 24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en", "de", "es", "fr", "hi", "it", "ja", "ko", "nl", "pl", "pt", "ru", "tr", "zh", "ar", "id", "sv"] }, { "model_id": "BTTS_V3", "display_name": "V3", "description": "Current-generation TTS. Bland's recommended model for new voices and integrations.", "sample_rates": [24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en"], "is_recommended": true }, { "model_id": "BTTS", "display_name": "V1", "description": "Legacy English-only TTS. Retained for backward compatibility. Prefer the recommended model for new integrations.", "sample_rates": [8000, 16000, 24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en"] } ]}
Overview
Returns the voice model generations (BTTS_V3, BTTS_V2, BTTS) with their clone eligibility and language list. Use it to map a voice’s service field to its generation, or to check which generations support Clone Voice.
Building on /v2/tts, /v2/tts/ws, or /v2/audio/speech? Use List TTS Models instead. It returns the encodings, sample rates, containers, and controls those endpoints accept. The sample_rates and max_characters fields here describe the legacy v1 speak endpoints, not the v2 request limits.
No authentication is required. Results are cached for up to 5 minutes.
Headers
string
Optional. This endpoint does not require authentication.
Response
array
Array of available models.
Show Model fields
string
Engine identifier. Use this to map a voice’s service field back to its model.
string
Human-readable name suitable for UI (for example V1, V2).
string
Short description of the model’s positioning.
number[]
Sample rates the legacy v1 speak endpoints support for this model.
number
Maximum characters per synthesis request supported by the model.
boolean
Whether Clone Voice can produce voices on this model.
string[]
Language codes supported for synthesis.
boolean
true for the model Bland currently recommends for new integrations.
{ "models": [ { "model_id": "BTTS_V2", "display_name": "V2", "description": "Previous-generation TTS with multilingual output and instant single-sample cloning. Prefer V3 where its language support fits.", "sample_rates": [8000, 16000, 24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en", "de", "es", "fr", "hi", "it", "ja", "ko", "nl", "pl", "pt", "ru", "tr", "zh", "ar", "id", "sv"] }, { "model_id": "BTTS_V3", "display_name": "V3", "description": "Current-generation TTS. Bland's recommended model for new voices and integrations.", "sample_rates": [24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en"], "is_recommended": true }, { "model_id": "BTTS", "display_name": "V1", "description": "Legacy English-only TTS. Retained for backward compatibility. Prefer the recommended model for new integrations.", "sample_rates": [8000, 16000, 24000, 44100], "max_characters": 1000, "can_clone": true, "languages": ["en"] } ]}