> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.talkif.ai/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.talkif.ai/_mcp/server.

# Models and voices

> Every speech-to-text, language and text-to-speech model Talkif offers, with languages, features and current per-unit prices — generated from the live catalogue.

The catalogue below is generated from the platform's live model list — the same one the builder's provider nodes show and the same rates the billing engine applies. Prices are per unit as billed: STT per minute of audio, LLM per million tokens (input and output separately), TTS per thousand characters synthesized. How those units turn into a call's cost is in [Credits and pricing](/concepts/credits-and-pricing); how to choose between them is in [Choose models and voices](/build/choose-models-and-voices).

Voices aren't listed here — each TTS provider has hundreds, and the list is live in the builder's voice selector (or [`GET /models/tts/voices`](/api-reference/ai-models/list-tts-voices)).

## Speech-to-text

#### AWS

| Model        | Per minute |
| ------------ | ---------- |
| `transcribe` | \$0.0100   |

#### Cartesia

| Model         | Per minute |
| ------------- | ---------- |
| `ink-whisper` | \$0.0023   |

#### Deepgram

| Model                     | Per minute |
| ------------------------- | ---------- |
| `nova-3-general`          | \$0.0077   |
| `nova-3-medical`          | \$0.0077   |
| `nova-2-general`          | \$0.0058   |
| `nova-2-conversationalai` | \$0.0058   |
| `nova-2-phonecall`        | \$0.0058   |

#### ElevenLabs

| Model                | Per minute |
| -------------------- | ---------- |
| `scribe_v2_realtime` | \$0.0065   |

#### Soniox

| Model       | Per minute |
| ----------- | ---------- |
| `stt-rt-v5` | \$0.0020   |

#### xAI

| Model      | Per minute |
| ---------- | ---------- |
| `grok-stt` | \$0.0033   |

## Language models

#### Anthropic

| Model              | Input / 1M tokens | Output / 1M tokens |
| ------------------ | ----------------- | ------------------ |
| `claude-opus-5`    | \$5.00            | \$25.00            |
| `claude-sonnet-5`  | \$2.00            | \$10.00            |
| `claude-haiku-4-5` | \$1.00            | \$5.00             |

#### Google

| Model                    | Input / 1M tokens | Output / 1M tokens |
| ------------------------ | ----------------- | ------------------ |
| `gemini-3.5-flash`       | \$1.50            | \$9.00             |
| `gemini-3.1-pro-preview` | \$2.00            | \$12.00            |
| `gemini-3.1-flash-lite`  | \$0.25            | \$1.50             |
| `gemini-3-flash-preview` | \$0.50            | \$3.00             |

#### Grok

| Model      | Input / 1M tokens | Output / 1M tokens |
| ---------- | ----------------- | ------------------ |
| `grok-4.5` | \$2.00            | \$6.00             |
| `grok-4.3` | \$1.25            | \$2.50             |

#### OpenAI

| Model           | Input / 1M tokens | Output / 1M tokens |
| --------------- | ----------------- | ------------------ |
| `gpt-5.6-sol`   | \$5.00            | \$30.00            |
| `gpt-5.6-terra` | \$2.00            | \$12.00            |
| `gpt-5.6-luna`  | \$0.20            | \$1.20             |
| `gpt-5.5`       | \$5.00            | \$30.00            |
| `gpt-5.4`       | \$2.50            | \$15.00            |
| `gpt-5.4-mini`  | \$0.75            | \$4.50             |
| `gpt-5.4-nano`  | \$0.20            | \$1.25             |
| `gpt-5.2`       | \$1.75            | \$14.00            |
| `gpt-5.1`       | \$1.25            | \$10.00            |
| `gpt-5`         | \$1.25            | \$10.00            |
| `gpt-5-mini`    | \$0.25            | \$2.00             |
| `gpt-4.1`       | \$2.00            | \$8.00             |
| `gpt-4.1-mini`  | \$0.40            | \$1.60             |
| `gpt-4o`        | \$2.50            | \$10.00            |
| `gpt-4o-mini`   | \$0.15            | \$0.60             |

Some models don't accept a temperature; the builder hides the setting for those. Reasoning-style models add thinking time before each reply — better for post-call analysis than for live conversation.

## Text-to-speech

#### Cartesia

| Model         | Per 1K characters |
| ------------- | ----------------- |
| `sonic-turbo` | \$0.0380          |
| `sonic-2`     | \$0.0380          |
| `sonic-3`     | \$0.0380          |

#### ElevenLabs

| Model                      | Per 1K characters |
| -------------------------- | ----------------- |
| `eleven_v4_turbo`          | \$0.0400          |
| `eleven_flash_v2_5`        | \$0.0400          |
| `eleven_v3_conversational` | \$0.0400          |
| `eleven_turbo_v2_5`        | \$0.0400          |

#### Google

| Model                  | Per 1K characters |
| ---------------------- | ----------------- |
| `gemini-2.5-flash-tts` | \$0.0170          |
| `gemini-2.5-pro-tts`   | \$0.0340          |

#### Rime

| Model    | Per 1K characters |
| -------- | ----------------- |
| `mistv2` | \$0.0300          |
| `coda`   | \$0.0500          |

#### xAI

| Model      | Per 1K characters |
| ---------- | ----------------- |
| `grok-tts` | \$0.0150          |

## Telephony

| Provider     | Inbound / min | Outbound / min |
| ------------ | ------------- | -------------- |
| SIP Trunking | \$0.0040      | \$0.0040       |
| Twilio       | \$0.0085      | \$0.0140       |
| WhatsApp     | Free          | Free           |

## By API

[`GET /models`](/api-reference/ai-models/list-providers-public) returns the same catalogue as JSON, including each model's capabilities — use it if you build flows programmatically and want to validate a model before publishing.