F5 TTS

Usage-based pricing
ae_f5_tts

Turn text into speech using the voice from a reference audio recording. Only F5-TTS is currently available.

TTSAudio
Usage-based pricing

Pricing

The charge per call is (max(60 × text input characters, 0)) AE credits. All applicable conditions are combined to calculate the total.

All available model options are charged based on input text characters. Automatic speech recognition is used when reference text is left empty, and silence removal is enabled by default. No separate charges for these options are listed in the available pricing information. This pricing description applies to normal successful calls and is not an absolute minimum for cases such as empty results.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.gen_textstringYesThe text to be converted to speech. Maximum 5000 characters.—
request_body.ref_textstringNoThe reference text to be used for TTS. If not provided, an ASR (Automatic Speech Recognition) model will be used to generate the reference text.""
request_body.model_typeenum (F5-TTS)YesThe name of the model to be used for TTS. Currently available values: F5-TTS.—
request_body.ref_audio_urlstringYesThe URL of the reference audio file.—
request_body.remove_silencebooleanNoWhether to remove the silence from the audio file.true

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_f5_tts' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "gen_text": "工具再火,\n得你能用上,\n那才叫真火!",
      "model_type": "F5-TTS",
      "ref_audio_url": "https://agentearth.ai/fileserver/file/18e4279f-b482-46f2-81f1-aad43f631ef5.mp3",
      "remove_silence": false
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "b7339ca5-7326-4d60-a8d4-28c82a075396"
}

Guides using this tool

See how this tool fits into real workflows

Text-to-Speech Model Comparison on One PlatformSynthesize the same script across multiple TTS models in parallel and let an AI agent compare voice, naturalness, language coverage, and emotion — run the whole shootout with one key and pick the right voice model.AI Lip-Sync Workflow: Swap Voice and Match MouthsUse an AI agent to swap the voiceover on an existing video and sync the mouths to it: drive dubbing and lip-sync in one natural-language chain for fast, scalable video localization.The AI Agent Tool Stack for Content CreatorsHand your whole content workflow to one AI agent: go from trending topics to cover images, voiceover and a finished short video — one prompt chains ideation to the final cut, with no hopping between four or five platforms.Podcast Content Repurposing with AI AgentsHand a podcast episode to an AI agent: auto-transcribe the audio, summarise and slice it into written content, then voice short audio clips — one episode becomes many formats, no manual editing.Chinese & Multilingual AI Voiceover (TTS): Batch Audio with AgentsTurn text into natural Chinese voiceover with an AI agent, with lively voices and multilingual support. Learn how to compare multiple TTS models, batch-generate audio in natural language, and feed it into digital-human video.Digital Human Talking-Head Video: One Photo and One Voice ClipTurn a single portrait photo and a voice clip into a digital-human talking-head video with an AI agent. Learn how the TTS-to-avatar chain works, which tools to use, and how to batch new scripts.