Dialogue tools

Generate single-voice text-to-speech audio on Replicate. The generate_dialogue tool accepts one prompt and one voice per call (multi-voice scenes are produced by stitching multiple calls), and supports two providers:

• ElevenLabs v3 (provider: "elevenlabs", the default) — 26 human-named voices, the most natural prosody.
• Google Gemini 3.1 Flash TTS (provider: "google") — 30 voices, 70+ languages, a natural-language style prompt, and inline expressive tags ([sigh], [laughing], [whispering], [shouting], [extremely fast], [like dracula]) that are actually performed.

Both bill at the same rate (26 credits / 1,000 characters). The full live catalog also flows through get_models (filter model_type: "speech").

#ElevenLabs v3 (default)

elevenlabs/v3 accepts these 26 voices (case-sensitive). Any value outside this list is rejected with 400 Unsupported voice and you are not charged. Audio tags like [laughs] are stripped server-side before synthesis (not spoken).

#Female voices

#Male voices

#Google Gemini 3.1 Flash TTS

Pass provider: "google". Gemini adds a natural-language style prompt (set the tone, pace, accent, emotion, or a character) and performs inline [tags] instead of stripping them. It accepts 30 voices (case-sensitive) and BCP-47 language codes.

Inline tags are performed, not stripped: [sigh], [laughing], [uhm], [whispering], [shouting], [sarcasm], [robotic], [extremely fast], [short pause] / [medium pause] / [long pause], and free-form descriptive tags like [like dracula] or [excitedly].

#Female voices

#Male voices

Languages: BCP-47 codes (e.g. en-US, en-GB, es-ES, es-MX, pt-BR, fr-FR, de-DE, it-IT, ja-JP, ko-KR, hi-IN, ar-001, ru-RU, ro-RO, tr-TR, vi-VN, th-TH, and 70+ more), or auto to auto-detect. Default en-US. Call get_limits_for_model('text-to-dialogue-gemini') for the full list.

#generate_dialogue

Generate a single-voice TTS clip.

Parameters:

ElevenLabs strips [HEY] / [laughs] / [whispers] before synthesis. Google performs inline tags — see the tag list above.

Example (Google Gemini):

{
  "provider": "google",
  "text": "[whispering] I have a secret. [laughing] Just kidding!",
  "voice": "Callirrhoe",
  "style_prompt": "Speak playfully, like sharing a fun secret with a friend.",
  "language_code": "en-US"
}

Example (ElevenLabs):

{
  "text": "Welcome back, ready to generate?",
  "voice": "Rachel",
  "stability": 0.5,
  "language_code": "en"
}

Response: Returns a generation_id. Poll with get_generation_status.

#Multi-voice scenes

generate_dialogue is single-voice. For dialogue between two speakers, call the tool once per line (ElevenLabs: pass previous_text / next_text for prosody continuity), then concatenate the resulting audio files yourself.

#get_generation_status

Use the generation_id returned by generate_dialogue to check progress. When the status is completed, the audio file URL is in the outputs array (media_type: "audio").

#Credits and limits

• Cost: 26 credits per 1,000 characters, both providers (rounding: decimal ≤ 0.3 floors, > 0.3 ceils).
• Minimum: 1 credit for any non-empty text.
• Minimum length: 5 characters after audio tags are stripped.
• Maximum length: ElevenLabs 5,000 characters; Google 4,000 bytes for text (and ≤ 8,000 bytes for text + style_prompt combined).

See Limitations for full details.